WO2017166155A1 - 一种对神经网络模型进行训练的方法、装置及电子设备 - Google Patents
一种对神经网络模型进行训练的方法、装置及电子设备 Download PDFInfo
- Publication number
- WO2017166155A1 WO2017166155A1 PCT/CN2016/077975 CN2016077975W WO2017166155A1 WO 2017166155 A1 WO2017166155 A1 WO 2017166155A1 CN 2016077975 W CN2016077975 W CN 2016077975W WO 2017166155 A1 WO2017166155 A1 WO 2017166155A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- neural network
- network model
- model
- layer
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
Definitions
- the present application relates to the field of information processing technologies, and in particular, to a method, device, and electronic device for training a neural network model.
- CNN Convolutional Neural Network
- the CNN model is a hierarchical model.
- FIG. 1 is a schematic diagram of the CNN model.
- the CNN model is composed of an input layer 101, a plurality of hidden layers 102, and an output layer 103.
- the input layer 101 provides data to be processed corresponding to the sample to be identified.
- the sample to be identified is a grayscale image
- the data to be processed is a two-dimensional matrix; the type of the hidden layer 102 may be a common convolution layer or a relaxed convolution.
- output layer 103 provides the final result of the model, for the CNN model used for classification, The output layer 103 outputs the probability that the sample to be identified belongs to each class.
- the large-scale CNN model has the following problems during training: a) The larger the model, the easier it is to overfit. ; b) The larger the model, the longer the training time required.
- the embodiment of the present application provides a method, a device, and an electronic device for training a neural network model, training a small-scale neural network model, and initializing a large-scale neural network model by a small-scale neural network model, and finally initializing The subsequent large-scale neural network model is fine-tuned, thereby avoiding problems such as over-fitting and excessive training time caused by direct training of large-scale neural networks.
- a method for training a neural network model for Determining the weights in the neural network model, the method comprising:
- Each weight in the initialized neural network model is adjusted based on a known training set.
- extracting a portion of the neural network model comprises:
- a portion of the neuron nodes in each of the hidden layers of the common convolutional neural network model are extracted to form the neural network sub-model.
- initializing each weight in the neural network model to form an initialization neural network model includes:
- the normal convolutional layer in the initialized general convolutional neural network model is transformed into a relaxed convolutional layer to form the initialized neural network model.
- initializing each weight in the neural network model to form an initialization neural network model includes:
- the normal convolutional layer in the adjusted ordinary convolutional neural network model is transformed into a relaxed convolutional layer to form the initialized neural network model.
- the initializing the common convolutional neural network model by initializing each weight in the common convolutional neural network model includes:
- the weights of corresponding hidden layers in the common convolutional neural network model are performed according to weights of respective hidden layers in the optimized neural network sub-model Initialization includes:
- the weights of the hidden layers in the optimized neural network sub-model are multiplied by predetermined coefficients as the weights of the corresponding hidden layers in the common convolutional neural network model.
- an apparatus for training a neural network model for determining weights in a neural network model comprising:
- An extracting unit for extracting a portion of the neural network model to form a neural network sub-model
- a first training unit for training the neural network sub-model to form an optimized neural network sub-model
- An initialization unit that initializes each weight in the neural network model according to each weight in the optimized neural network sub-model to form an initialization neural network model, and the initialization neural network model and the optimization Neural network submodels have the same output characteristics;
- a second training unit that adjusts weights in the initialized neural network model based on a known training set.
- the extracting unit includes:
- a first conversion unit for converting a relaxed convolutional layer in the neural network model into a common convolutional layer to convert the neural network model into a general convolutional neural network model
- An extraction subunit is configured to extract a partial neuron node in each hidden layer of the common convolutional neural network model to form the neural network submodel.
- the initialization unit includes:
- a first initialization subunit configured to initialize each weight in the common convolutional neural network model according to each weight in the optimized neural network submodel to form an initialization common convolutional neural network model
- a second transformation unit for converting a common convolutional layer in the initialized general convolutional neural network model into a relaxed convolutional layer to form the initialization neural network model.
- the initializing unit includes:
- a second initialization subunit initializing the Pu according to each weight in the optimized neural network submodel
- the weights in the convolutional neural network model are used to form an initial general convolutional neural network model
- a third training unit that adjusts weights in the initialized general convolutional neural network model based on a known training set to form an adjusted general convolutional neural network model
- a third transformation unit for converting a common convolutional layer in the adjusted general convolutional neural network model into a relaxed convolutional layer to form the initialization neural network model.
- the first initializing subunit corresponds to the weight of each hidden layer in the optimized neural network submodel, to the common convolutional neural network model
- the weights of the hidden layers are initialized to form an initial general convolutional neural network model, wherein the output characteristics of the implicit layers of the normalized convolutional neural network model are initialized with each of the optimized neural network submodels
- the output characteristics of the hidden layer are the same.
- the first initializing subunit multiplies weights of the hidden layer in the optimized neural network submodel by a predetermined coefficient as the ordinary convolution The weights of the corresponding hidden layers in the neural network model.
- an electronic device comprising the apparatus for training a neural network model according to any one of the seventh to twelfth aspects of the embodiments.
- a fourteenth aspect of the embodiments of the present application there is provided a computer readable program, wherein when the program is executed in a device or an electronic device that trains a neural network model, the program causes the pair of neural networks
- the apparatus or apparatus for training the model performs the method of training the neural network model described in any one of the first to sixth aspects of the above embodiments.
- a storage medium storing a computer readable program, wherein the storage medium stores the computer readable program of the fourteenth aspect of the above embodiment, the computer readable program A device or an electronic device that trains a neural network model performs the method of training a neural network model as described in any one of the first to sixth aspects of the above embodiments.
- the beneficial effects of the embodiments of the present application are: shortening the training time of large-scale neural networks and avoiding over-fitting problems.
- Figure 1 is a schematic diagram of a CNN model
- FIG. 2 is a schematic diagram of a neural network model of Embodiment 1;
- FIG. 3 is a schematic diagram of a method of training a neural network model of Embodiment 1;
- FIG. 4 is a schematic diagram of a method of extracting a portion of a neural network model of Embodiment 1;
- FIG. 5 is a schematic diagram of a conventional convolutional neural network model of Embodiment 1;
- Figure 6 is a schematic view showing a treatment mode of the slack convolution layer of the first embodiment
- FIG. 7 is a schematic diagram showing a processing manner of a general convolution layer of Embodiment 1;
- FIG. 8 is a schematic diagram of a neural network sub-model of Embodiment 1;
- FIG. 9 is a schematic diagram of a method for initializing weights in a neural network model in Embodiment 1;
- Figure 10 (A) is a schematic diagram of an input layer and a convolution layer of the optimized neural network sub-model
- Figure 10 (B) is a schematic diagram of an input layer and a convolution layer of an ordinary convolutional neural network model after initialization;
- Figure 11 (A) is a schematic diagram of a pooled layer and a convolutional layer of the optimized neural network sub-model
- Figure 11 (B) is a schematic diagram of a pooling layer and a convolution layer of an ordinary convolutional neural network model after initialization;
- Figure 12 (A) is a partial schematic view of the pooling layer and the convolution layer of Figure 11 (A);
- Figure 12 (B) is a partial schematic view of the pooling layer and the convolution layer of Figure 11 (B);
- Figure 13 (A) is a schematic diagram of the fully connected layer of the optimized neural network sub-model and its previous hidden layer
- Figure 13 (B) is a schematic diagram of the fully connected layer of the normal convolutional neural network model after initialization and its previous hidden layer;
- Figure 14 (A) is a partial schematic view of the fully connected layer of Figure 13 (A) and its previous hidden layer;
- Figure 14 (B) is a partial schematic view of the fully connected layer of Figure 13 (B) and its previous hidden layer;
- FIG. 15 is another schematic diagram of a method for initializing weights in a neural network model in Embodiment 1;
- FIG. 16 is a schematic diagram of an apparatus for training a neural network model of Embodiment 2;
- Figure 17 is a schematic illustration of the extraction unit of Embodiment 2.
- Figure 18 is a schematic diagram of an initialization unit of Embodiment 2;
- Figure 19 is another schematic diagram of the initialization unit of Embodiment 2.
- 20 is a schematic block diagram showing the system configuration of the electronic device 2000 of the third embodiment.
- Embodiment 1 of the present application provides a method of training a neural network model for determining weights in a neural network model.
- the neural network model 200 includes an input layer 201, a convolution layer 202, a pooling layer 203, a relaxed convolution layer 204, and a fully connected layer 205. And the output layer 206, wherein the convolution layer 202, the pooling layer 203, the relaxed convolution layer 204, and the fully connected layer 205 are all hidden layers.
- the input layer 201 can input the data to be identified 2011; each of the convolutional layer 202, the pooling layer 203, the relaxed convolutional layer 204, the fully connected layer 205, and the output layer 206 receives the upper layer.
- the output data is processed by the weight corresponding to the layer to generate the data output by the layer and output from the neuron node (neuron) of the layer, and the neuron nodes of each layer are respectively 2021-2024, 2031-2034, 2041-2046, 2051-2058, and 2061-20610, and, based on the data output by the neuron node of the output layer 206, the probability that the data to be identified 2011 belongs to each category 206a can be determined; further, in FIG. 2, only the marker Neuron nodes 2021, 2024, 2031, 2034, 2041, 2046, 2051, 2058, 2061, and 20610 are excluded, and other neuron nodes are not marked.
- the data to be identified 2011 input by the input layer 201 may be a handwritten digital image, a convolution layer 202, a pooling layer 203, and a slack convolution layer.
- the data output by the neuron node of 204 may be a feature map, and the data output by the neuron nodes of the fully connected layer 205 and the output layer 206 may be numerical values.
- a number in the numbers 0-9 may correspond to a category 206a. Therefore, based on the data output by the output layer 206, the probability that the data to be identified 2011 belongs to each of 0-9 can be determined.
- the weights corresponding to each layer are selected to ensure that the classification result output by the output layer 206 is accurate, wherein the weight corresponding to each layer may be a matrix of m*n, m And n are both natural numbers.
- the method for training the neural network model in this embodiment is for determining the weight corresponding to each layer in the neural network model.
- the neural network model 200 has a relaxed convolution layer 204. Therefore, the neural network model 200 belongs to a convolutional neural network model.
- the neural network model 200 of the present embodiment may not have The relaxation convolution layer 204 is not limited in this embodiment; and the method for training the neural network model described in this embodiment is applicable not only to the convolutional neural network model but also to other neural network models.
- FIG. 3 is a schematic diagram of a method for training a neural network model according to the embodiment. As shown in FIG. 3, the method includes:
- the trained sub-model is used to initialize a large-scale neural network model, and then fine-tuning a large-scale neural network model.
- the method of the present embodiment can avoid problems such as overfitting and excessive training time as compared with a method of directly training a large-scale neural network model.
- FIG. 4 is a schematic diagram of a method of extracting a part of a neural network model of the embodiment, as shown in FIG. 4, the method includes:
- step S401 the relaxed convolutional layer 204 in the neural network model 200 of FIG. 2 is converted into a normal convolutional layer, thereby transforming the neural network model 200 from a convolutional neural network model to a general convolutional neural network model.
- FIG. 5 is a schematic diagram of the conventional convolutional neural network model 500 in which the relaxed convolutional layer 204 is transformed into a common convolutional layer 504, and the other layers of the conventional convolutional neural network model 500 are identical to the neural network model 200.
- the data processing manner of the ordinary convolutional layer 504 is different from the data processing manner of the slack convolutional layer 204 in that, in the ordinary convolutional layer 504, data sharing at different locations within the same neuron node participating in the convolution operation is performed.
- a weight, and in the relaxed convolutional layer 204, data at different locations within the same neuron node participating in the convolution operation does not share any of the weights.
- FIG. 6 is a schematic diagram of the processing manner of the slack convolution layer 204 of the present embodiment.
- P1 and P2 are different neuron nodes participating in the convolution operation
- P11 and P14 are different positions in P1.
- Data, P21, P24 are data of different positions in P2, W11, W14, W21, W24 are different weights
- T11 and T14 are data generated after convolution operation, wherein T11 and T14 are calculated as follows ( 1), (2):
- the data P11 and P14 in the neuron node P1 correspond to independent weights W11 and W14, respectively, and the data P21 and P24 in the neuron node P2 respectively correspond to independent rights.
- Value W21, W24 that is, data at different locations within the same neuron node does not share any weight.
- T11 and T14 are calculated as shown in the following equations (3) and (4):
- the data P11 and P14 at different positions in the neuron node P1 share the weight W1
- the data P21 and P24 at different positions in the neuron node P2 share the weight W2.
- step S401 of the present embodiment part of the weights in the relaxed convolution layer 204 of the neural network model 200 may be deleted to reduce the number of weights, thereby causing the same neuron node to participate in the convolution operation
- the data shares a weight, thereby transforming the relaxed convolutional layer 204 into a normal convolutional layer 504 to convert the neural network model 200 into a normal convolutional neural network model 500.
- step S402 of the present embodiment the neuron nodes of each hidden layer of the ordinary convolutional neural network model 500 can be deleted according to a certain ratio, thereby obtaining a neural network sub-model, in which each hidden layer is deleted.
- the proportion of neuron nodes can be the same or different.
- FIG. 8 is a schematic diagram of the neural network sub-model 800 of the present embodiment.
- the proportion of neurons in each hidden layer is deleted. 50%, thereby forming a neural network sub-model 800, wherein 801 of FIG. 8 is a neuron node deleted from the ordinary convolutional neural network model 500, and the input layer 201 and the output layer 206 of FIG. 8 are respectively associated with FIG.
- the input layer 201 is the same as the output layer 206, and the convolutional layer 802, the pooling layer 803, the convolutional layer 804, and the fully connected layer 805 of FIG. 8 and the convolutional layer 202, the pooling layer 203, and the ordinary convolutional layer 504 of FIG.
- the fully connected layers 205 correspond to each.
- the neural network model 200 is first converted into a common convolutional neural network model, and then the neuron node is deleted from the common convolutional neural network model to obtain the neural network sub-model 800.
- the purpose of transforming the neural network model 200 into a common convolutional neural network model is to reduce the number of weights in the subsequently generated neural network sub-model 800 and avoid over-fitting.
- the present embodiment is not limited thereto. If the neural network model 200 does not have the slack convolution layer 204, the neuron node 200 can be directly deleted by the neural network model 200.
- the neural network sub-model 800 can be trained according to a known training set to determine an optimized value of each weight thereof, thereby training the neural network sub-model 800 as an optimized god. Through the network sub-model.
- the method for training the neural network sub-model 800 can refer to the prior art, and details are not described in this embodiment.
- the optimized neural network submodel can be used to initialize the weights in the neural network model 200, and the initialized neural network model 200 has the same neural network submodel as the optimized neural network.
- FIG. 9 is a schematic diagram of a method for initializing each weight in the neural network model according to the embodiment, for implementing step S303. As shown in FIG. 9, the method includes:
- S901 Initialize, according to each weight in the optimized neural network submodel, each weight in the common convolutional neural network model to form an initial common convolutional neural network model;
- the weights of the corresponding hidden layers in the common convolutional neural network model 500 may be initialized according to the weights of the hidden layers in the optimized neural network submodel.
- the weights of the hidden layers in the optimized neural network submodel are multiplied by a predetermined coefficient as the weights of the corresponding hidden layers in the general convolutional neural network model.
- convolutional layer 202 is coupled to input layer 201, which is the first hidden layer after input layer 201.
- the input data of the convolutional layer 202 is the data to be identified of the input layer 201, and the data to be identified is convoluted with the weight of the convolutional layer 202 to obtain the output data of each neuron node of the convolutional layer 202.
- FIG. 10(A) is a schematic diagram of the input layer 201 and the convolution layer 802 of the optimized neural network sub-model 800
- FIG. 10(B) is the input layer 201 and the convolution layer of the initialized normal convolutional neural network model 500.
- the input data is convoluted with the weight K1 to obtain the feature map A1 output by the neuron node 8021, and the input data is convoluted with the weight K2 to obtain the feature map A2.
- the weight K1 is multiplied by a predetermined coefficient L11 as a common convolutional neural network submodel 500 volume.
- the weights corresponding to the neuron nodes 2021, 2023 of the layer 202 multiply the weight K2 by a predetermined coefficient L12, which corresponds to the neuron nodes 2022, 2024 of the convolutional layer 202 of the common convolutional neural network submodel 500.
- the weights are thus initialized for each weight of the convolutional layer 202 of the normal convolutional neural network model 500.
- the predetermined coefficients L11 and L12 may both be 1, and therefore, the feature maps output by the neuron nodes 2021, 2022, 2023, and 2024 of the convolutional layer 202 of the common convolutional neural network model 500 are respectively A1.
- L11, L12 may have other values, and may be different from each other.
- the feature map output by each neuron node of the convolution layer 202 is used as input data of the pooling layer 203
- the feature map output by the pooling layer 203 is used as input data of the convolution layer 504
- the convolution layer 504 is a non-first hidden layer.
- FIG. 11(A) is a schematic diagram of the pooled layer 803 and the convolution layer 804 of the optimized neural network submodel 800
- FIG. 11(B) is the pooled layer 203 and volume of the initialized normal convolutional neural network model 500.
- the feature maps B1, B2 outputted by the respective neuron nodes of the pooling layer 803 are used to generate feature maps C1-C3 of the respective neuron nodes of the convolutional layer 804.
- A1 and A2 of FIG. 10(A) and the corresponding weights are respectively pooled to obtain B1 and B2.
- the feature maps B1-B4 outputted by the respective neuron nodes of the pooling layer 203 are used to generate feature maps C1'-C6' of the respective neuron nodes of the convolutional layer 504.
- A1-A4 of FIG. 10(B) and the corresponding weights are respectively pooled to obtain B1-B4, and each weight in the pooling layer 203 may be pooled.
- the pooling layer 203 of the product neural network model 500 has the same output characteristics as the pooling layer 803 of the optimized neural network submodel 800.
- FIG. 12(A) is a partial schematic view of the pooling layer 803 and the convolution layer 804 of FIG. 11(A)
- FIG. 12(B) is a partial schematic view of the pooling layer 203 and the convolution layer 504 of FIG. 11(B).
- Figures 12(A) and 12(B) the corresponding weights are shown.
- the weight K3 is multiplied by a predetermined coefficient L21 to obtain K3' as the weight corresponding to the feature maps B1, B3 in the convolutional layer 504 of the ordinary convolutional neural network submodel 500.
- the weights of the convolutional layer 504 of the model 500 are initialized.
- C1' C1
- the convolutional layer 504 of the normalized convolutional neural network model 500 after initialization has the same output characteristics as the convolutional layer 804 of the optimized neural network submodel 800.
- L21, L22 may have other values, and may be different from each other.
- the weight between B1, B4, and C2' of FIG. 11(B) can be used in a similar manner to the above, using the weights between B1, B2, and C2 of FIG. 11(A).
- the weight between B1, B4 and C4' of Fig. 11(B) can be used in a similar manner to the above, using the weights between B1, B2 and C1 of Fig. 11(A).
- the weight between B1, B4, and C5' of FIG. 11(B) can be initialized using the weights between B1, B2, and C2 of FIG. 11(A), using FIG. 11(A).
- the initialization methods of the weights in the other convolutional layers are similar to the initialization methods for the weights in the convolutional layer 504.
- the fully connected layer 205 may be located after all the convolutional layers, and the output layer 206 may be connected to the rear of the fully connected layer 205, that is, the fully connected layer 205 is the last hidden layer, or the fully connected layer.
- Other fully connected layers may be connected to the rear of 205, i.e., the fully connected layer 205 is a non-final hidden layer.
- the initialization method of each weight of the fully-connected layer 205 may refer to the initialization method of the convolution layer 504 located after the first hidden layer, and at the fully-connected layer.
- the convolution operation is replaced by a multiplication operation because the fully-connected layer 205 can be regarded as a convolutional layer having a weight of 1 ⁇ 1.
- the fully connected layer 205 which is the last hidden layer, has as many neuron nodes as the number of classes of the output layer 206. Therefore, for the fully connected layer 805 of the optimized neural network submodel 800 and the fully connected layer 205 of the initialized normal convolutional neural network model 500, the number of neuron nodes is the same, but the input data of the two The number can vary.
- FIG. 13(A) is a schematic diagram of the fully connected layer 805 of the optimized neural network submodel 800 and its previous hidden layer
- FIG. 13(B) is the fully connected layer 205 of the initialized normal convolutional neural network model 500.
- a schematic diagram of the previous hidden layer is a schematic diagram of the previous hidden layer.
- the data F1, F2 outputted by the neuron nodes of the previous hidden layer are used to generate the output data E1-E3 of the respective neuron nodes of the fully connected layer 805.
- the data F1-F4 outputted by the respective neuron nodes of the previous hidden layer are used to generate the output data E1'-E3' of the respective neuron nodes of the fully connected layer 205.
- the data F1-F4 may be in the form of a floating point number.
- the number of neuron nodes of the previous hidden layer is reduced by half compared with the number of the previous hidden layer of FIG. 13(B) due to the operation of the previous extraction submodel.
- the number of data outputted by the previous hidden layer in Fig. 13(A) is also half the number of data outputted by the previous hidden layer in Fig. 13(B).
- Figure 14 (A) is a partial schematic view of the fully-connected layer 805 of Figure 13 (A) and its previous hidden layer
- Figure 14 (B) is the fully-connected layer 205 of Figure 13 (B) and its previous hidden layer
- F1 and F2 are multiplied by weights K5 and K6 to obtain data E1 outputted by the neuron node 8051, and the multiplication is as shown in the following equation (7):
- the weight K5 is multiplied by a predetermined coefficient L31 to obtain K5', which is the weight corresponding to F1 and F3 in the fully connected layer 205 of the ordinary convolutional neural network model 500.
- the value K6 is multiplied by a predetermined coefficient L32 to obtain K5' as the weight corresponding to F2 and F4 in the fully connected layer 205 of the ordinary convolutional neural network model 500, thereby the fully connected layer of the ordinary convolutional neural network model 500.
- the weights of 205 are initialized.
- E1' E1
- the fully connected layer 205 of the initialized normal convolutional neural network model 500 has the same output characteristics as the fully connected layer 805 of the optimized neural network submodel 800.
- L31 and L32 may have other values, and may be different from each other.
- the weight between F1, F4 and E2' of Fig. 13(B) can be used in a similar manner to the above, using the weights between F1, F2 and E2 of Fig. 13(A).
- the weights in the ordinary convolutional neural network model 500 shown in FIG. 5 can be initialized.
- the general convolutional neural network model 500 is not limited to the result shown in FIG. 5.
- the ordinary convolutional neural network model 500 may have other hidden layers.
- the process of converting the normal convolution layer into the slack convolution layer may be the reverse process of step S401, that is, in step S902, the weights in the ordinary convolution layer may be copied in multiple copies.
- the data of different positions in the same neuron node participating in the convolution operation are corresponding to different weights. For example, the weight W1 in FIG. 7 is copied into W11 and W14, and the weight W2 is copied into W21 and W24. Thereby, the ordinary convolution layer is converted into a relaxed convolution layer.
- FIG. 15 is another schematic diagram of a method for initializing each weight in the neural network model in the embodiment, for implementing step S303. As shown in Figure 15, the method includes:
- S901 Initialize, according to each weight in the optimized neural network submodel, each weight in the common convolutional neural network model to form an initial common convolutional neural network model;
- step S1501 is added to the method of FIG. 15, that is, after the normal convolutional neural network model is initialized, the ordinary convolutional neural network model is adjusted by Thereby, the amount of work when the adjustment is performed in step S304 can be alleviated.
- step S1501 reference may be made to the method for adjusting the neural network model in the prior art, which is not described in this embodiment.
- the processing method of converting the ordinary convolution layer into the slack convolution layer in step S1502 may be the same as the processing method of step S902.
- the weights in the normal convolutional neural network model are initialized in step S901, and the ordinary convolution layer is converted into a slack volume by step S902 or steps S1501 and S1502.
- the layers are layered to initialize the weights of the neural network model 200; however, the embodiment is not limited thereto, and if the neural network model 200 does not have a relaxed convolutional layer, the neural network model 200 may be directly used in step S901.
- the weights are initialized without step S902 or steps S1501 and S1502.
- the weights in the initialization neural network model may be adjusted based on the known training set, and the manner of the adjustment may be referred to the prior art, which is not described in detail in this embodiment.
- a small-scale neural network model is trained, and a large-scale neural network model is initialized by a small-scale neural network model, and finally a large-scale neural network model after initialization is fine-tuned due to a small-scale network.
- Most of the training work has been completed, so large-scale networks only need to be fine-tuned for several rounds to converge, thereby avoiding over-fitting and excessive training time for direct training of large-scale neural networks. problem.
- Embodiment 2 provides an apparatus for training a neural network model, which corresponds to the method of Embodiment 1.
- the apparatus 1600 includes: an extracting unit 1601, a first training unit 1602, and an initializing unit 1603. And a second training unit 1604.
- the extracting unit 1601 is configured to extract a part of the neural network model to form a neural network sub-model; the first training unit 1602 is configured to train the neural network sub-model to form an optimized neural network sub-model; and the initializing unit 1603 Initializing each weight in the neural network model according to each weight in the optimized neural network sub-model to form an initialization neural network model, and the initializing the neural network model and the optimized neural network
- the models have the same output characteristics; the second training unit 1604 adjusts the weights in the initialized neural network model based on the known training set.
- the extracting unit 1601 includes a first converting unit 1701 and an extracting subunit 1702.
- the first conversion unit 1701 is configured to convert the relaxed convolution layer in the neural network model into a common convolution layer to convert the neural network model into a common convolutional neural network model; and the extraction subunit 1702 is used to A portion of the neuron nodes in each of the hidden layers of the common convolutional neural network model are extracted to form the neural network sub-model.
- FIG. 18 is a schematic diagram of the initialization unit 1603 of the second embodiment. As shown in FIG. 18, the initialization unit 1603 includes a first initialization subunit 1801 and a second conversion unit 1802.
- the first initialization subunit 1801 is configured to initialize each weight in the common convolutional neural network model according to each weight in the optimized neural network submodel to form an initialization common convolutional neural network model;
- the second transforming unit 1802 is configured to convert the normal convolutional layer in the initialized normal convolutional neural network model into a relaxed convolutional layer to form the initialized neural network model.
- the first initialization subunit 1801 may determine the weight of the corresponding hidden layer in the common convolutional neural network model according to the weight of each hidden layer in the optimized neural network submodel. Initializing to form an initialization common convolutional neural network model, wherein the output characteristics of the implicit layers of the initialized general convolutional neural network model are the same as the output characteristics of the hidden layers of the optimized neural network submodel For example, the first initialization subunit 1801 may multiply each weight of the hidden layer in the optimized neural network submodel by a predetermined coefficient as a corresponding hidden layer in the common convolutional neural network model. The weights of each.
- the second converting unit 1802 may convert the ordinary convolutional neural network model into a relaxed convolutional neural network model by using an operation opposite to that of the first converting unit 1701.
- FIG. 19 is another schematic diagram of the initializing unit 1603 of the second embodiment.
- the initializing unit 1603 includes: a second initializing subunit 1901, a third training unit 1902, and a third converting unit. 1903.
- the second initialization subunit 1901 initializes each weight in the common convolutional neural network model according to each weight in the optimized neural network submodel to form an initial common convolutional neural network model;
- the training unit 1902 adjusts each weight in the initialized normal convolutional neural network model to form an adjusted ordinary convolutional neural network model based on the known training set;
- the third transformation unit 1903 is configured to use the adjusted normal volume
- the ordinary convolutional layer in the neural network model is transformed into a relaxed convolutional layer to form the initialized neural network model.
- the processing manner of the second initialization subunit 1901 may be the same as the processing manner of the first initialization subunit 1801; and the manner in which the third training unit 1902 adjusts the weights in the normal convolutional neural network model.
- the third conversion unit 1903 may refer to the second conversion unit 1802 by converting the ordinary convolution layer into a relaxed convolution layer.
- a small-scale neural network model is trained, and a large-scale neural network model is initialized by a small-scale neural network model, and finally a large-scale neural network model after initialization is fine-tuned due to a small-scale network.
- Most of the training work has been completed, so large-scale networks only need to be fine-tuned for several rounds to converge, thereby avoiding over-fitting and excessive training time for direct training of large-scale neural networks. problem.
- Embodiment 3 of the present application provides an electronic device including the device for training a neural network model as described in Embodiment 2.
- FIG. 20 is a schematic block diagram showing the system configuration of an electronic device 2000 according to an embodiment of the present invention.
- the electronic device 2000 can include a central processor 2100 and a memory 2140; the memory 2140 is coupled to the central processor 2100.
- the figure is exemplary; other types of structures may be used in addition to or in place of the structure to implement telecommunications functions or other functions.
- the functionality of the device that trains the neural network model can be integrated into the central processor 2100.
- the central processing unit 2100 can be configured to:
- the neural network model has the same output characteristics as the optimized neural network sub-model; and the weights in the initialized neural network model are adjusted based on the known training set.
- the central processing unit 2100 may be further configured to: convert the relaxed convolution layer in the neural network model into a common convolution layer to convert the neural network model into a common convolutional neural network model; extract the A part of the neuron nodes in each hidden layer of the general convolutional neural network model to form the neural network sub-model.
- the central processing unit 2100 may be further configured to initialize each weight in the common convolutional neural network model according to each weight in the optimized neural network sub-model to form an initialized common convolutional neural network. a model; transforming a common convolutional layer in the initialized general convolutional neural network model into a relaxed convolutional layer to form the initialized neural network model.
- the central processing unit 2100 may be further configured to initialize each weight in the common convolutional neural network model according to each weight in the optimized neural network sub-model to form an initialized common convolutional neural network.
- Model based on the known training set, adjusting the weights in the initial general convolutional neural network model to form an adjusted ordinary convolutional neural network model; and the ordinary volume in the adjusted ordinary convolutional neural network model
- the laminate is converted into a relaxed convolutional layer to form the initialized neural network model.
- the central processing unit 2100 may be further configured to: perform weights of corresponding hidden layers in the common convolutional neural network model according to weights of respective hidden layers in the optimized neural network sub-model Initializing to form an initialization common convolutional neural network model, wherein the output characteristics of the implicit layers of the initialized normal convolutional neural network model are the same as the output characteristics of the hidden layers of the optimized neural network submodel.
- the central processing unit 2100 may be further configured to: multiply each weight of the hidden layer in the optimized neural network sub-model by a predetermined coefficient as a corresponding implicit in the common convolutional neural network model Contains the weights of the layers.
- the apparatus for training the neural network model may be configured separately from the central processing unit 2100.
- the apparatus for training the neural network model may be configured as a chip connected to the central processing unit 2100 through the central processing unit. Control to implement the functionality of the device that trains the neural network model.
- the electronic device 2000 may further include: a communication module 2110, an input unit 2120, an audio processing unit 2130, a display 2160, and a power source 2170. It should be noted that the electronic device 2000 does not have to include all the components shown in FIG. 20; in addition, the electronic device 2000 may further include components not shown in FIG. 20, and reference may be made to the prior art.
- central processor 2100 also sometimes referred to as a controller or operational control, can include a microprocessor or other processor device and/or logic device that receives input and controls each of electronic devices 2000. The operation of the part.
- the memory 2140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, or other suitable device, and may store a program for executing related information. . And the central processing unit 2100 can execute the program stored by the memory 2140 to implement information storage or processing and the like. The functions of other components are similar to those of the existing ones and will not be described here.
- the various components of electronic device 2000 may be implemented by special purpose hardware, firmware, software, or a combination thereof without departing from the scope of the invention.
- the embodiment of the present application further provides a computer readable program, wherein the program causes the information processing device or the electronic device to perform the pair of nerves described in Embodiment 1 when the program is executed in an information processing device or an electronic device The method of training the network model.
- the embodiment of the present application further provides a storage medium storing a computer readable program, wherein the storage medium stores the computer readable program, wherein the computer readable program causes the information processing device or the electronic device to perform the embodiment 1 A method of training a neural network model.
- the apparatus for training a neural network model described in connection with an embodiment of the present invention may be directly embodied as hardware, a software module executed by a processor, or a combination of both.
- one or more of the functional block diagrams shown in Figures 16-19 and/or one or more combinations of functional block diagrams may correspond to a computer program flow
- Each software module can also correspond to each hardware module.
- These software modules may correspond to the respective steps shown in Embodiment 1, respectively.
- These hardware modules can be implemented, for example, by curing these software modules using a Field Programmable Gate Array (FPGA).
- FPGA Field Programmable Gate Array
- the software module can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.
- a storage medium can be coupled to the processor to enable the processor to read information from, and write information to, the storage medium; or the storage medium can be an integral part of the processor.
- the processor and the storage medium can be located in an ASIC.
- the software module can be stored in the memory of the mobile terminal or in a memory card that can be inserted into the mobile terminal.
- the software module can be stored in the MEGA-SIM card or a large-capacity flash memory device.
- One or more of the functional block diagrams described with respect to Figures 16-19 and/or one or more combinations of functional block diagrams may be implemented to perform the functions described herein.
- DSP digital signal processor
- ASIC application specific integrated circuit
- FPGA field programmable gate array
- One or more of the functional blocks described with respect to Figures 16-19 and/or one or more combinations of functional blocks may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, multiple microprocessors One or more microprocessors in conjunction with DSP communication or any other such configuration.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (13)
- 一种对神经网络模型进行训练的方法,用于确定神经网络模型中的各权值,该方法包括:提取神经网络模型的一部分,以形成神经网络子模型;对所述神经网络子模型进行训练,以形成优化的神经网络子模型;根据所述优化的神经网络子模型中的各权值,初始化所述神经网络模型中的各权值,以形成初始化神经网络模型,并且,所述初始化神经网络模型与所述优化的神经网络子模型具有相同的输出特性;基于已知训练集,对所述初始化神经网络模型中的各权值进行调整。
- 如权利要求1所述的对神经网络模型进行训练的方法,其中,提取神经网络模型的一部分包括:将所述神经网络模型中的松弛卷积层转化为普通卷积层,以将所述神经网络模型转化为普通卷积神经网络模型;以及提取所述普通卷积神经网络模型的每一个隐含层中的部分神经元节点,以形成所述神经网络子模型。
- 如权利要求2所述的对神经网络模型进行训练的方法,其中,初始化所述神经网络模型中的各权值,以形成初始化神经网络模型包括:根据所述优化的神经网络子模型中的各权值,初始化所述普通卷积神经网络模型中的各权值,以形成初始化普通卷积神经网络模型;以及将所述初始化普通卷积神经网络模型中的普通卷积层转化为松弛卷积层,以形成所述初始化神经网络模型。
- 如权利要求2所述的对神经网络模型进行训练的方法,其中,初始化所述神经网络模型中的各权值,以形成初始化神经网络模型包括:根据所述优化的神经网络子模型中的各权值,初始化所述普通卷积神经网络模型中的各权值,以形成初始化普通卷积神经网络模型;基于已知训练集,对初始化普通卷积神经网络模型中的各权值进行调整,以形成调整后普通卷积神经网络模型;以及将所述调整后普通卷积神经网络模型中的普通卷积层转化为松弛卷积层,以形成 所述初始化神经网络模型。
- 如权利要求3所述的对神经网络模型进行训练的方法,其中,初始化所述普通卷积神经网络模型中的各权值,以形成初始化普通卷积神经网络模型包括:根据所述优化的神经网络子模型中的各隐含层的权值,对所述普通卷积神经网络模型中对应的隐含层的权值进行初始化,以形成初始化普通卷积神经网络模型,其中,所述初始化普通卷积神经网络模型的各隐含层的输出特性与所述优化的神经网络子模型的各隐含层的输出特性相同。
- 如权利要求5所述的对神经网络模型进行训练的方法,其中,根据所述优化的神经网络子模型中的各隐含层的权值,对所述普通卷积神经网络模型中对应的隐含层的权值进行初始化包括:将所述优化的神经网络子模型中的隐含层的各权值乘以预定的系数,作为所述普通卷积神经网络模型中的对应的隐含层的各权值。
- 一种对神经网络模型进行训练的装置,用于确定神经网络模型中的各权值,该装置包括:提取单元,其用于提取神经网络模型的一部分,以形成神经网络子模型;第一训练单元,其用于对所述神经网络子模型进行训练,以形成优化的神经网络子模型;初始化单元,其根据所述优化的神经网络子模型中的各权值,初始化所述神经网络模型中的各权值,以形成初始化神经网络模型,并且,所述初始化神经网络模型与所述优化的神经网络子模型具有相同的输出特性;第二训练单元,其基于已知训练集,对所述初始化神经网络模型中的各权值进行调整。
- 如权利要求7所述的对神经网络模型进行训练的装置,其中,所述提取单元包括:第一转化单元,其用于将所述神经网络模型中的松弛卷积层转化为普通卷积层,以将所述神经网络模型转化为普通卷积神经网络模型;以及提取子单元,其用于提取所述普通卷积神经网络模型的每一个隐含层中的部分神经元节点,以形成所述神经网络子模型。
- 如权利要求8所述的对神经网络模型进行训练的装置,其中,所述初始化单 元包括:第一初始化子单元,其用于根据所述优化的神经网络子模型中的各权值,初始化所述普通卷积神经网络模型中的各权值,以形成初始化普通卷积神经网络模型;以及第二转化单元,其用于将所述初始化普通卷积神经网络模型中的普通卷积层转化为松弛卷积层,以形成所述初始化神经网络模型。
- 如权利要求8所述的对神经网络模型进行训练的装置,其中,所述初始化单元包括:第二初始化子单元,根据所述优化的神经网络子模型中的各权值,初始化所述普通卷积神经网络模型中的各权值,以形成初始化普通卷积神经网络模型;第三训练单元,其基于已知训练集,对初始化普通卷积神经网络模型中的各权值进行调整,以形成调整后普通卷积神经网络模型;以及第三转化单元,其用于将所述调整后普通卷积神经网络模型中的普通卷积层转化为松弛卷积层,以形成所述初始化神经网络模型。
- 如权利要求9所述的对神经网络模型进行训练的装置,其中,所述第一初始化子单元根据所述优化的神经网络子模型中的各隐含层的权值,对所述普通卷积神经网络模型中对应的隐含层的权值进行初始化,以形成初始化普通卷积神经网络模型,其中,所述初始化普通卷积神经网络模型的各隐含层的输出特性与所述优化的神经网络子模型的各隐含层的输出特性相同。
- 如权利要求11所述的对神经网络模型进行训练的装置,其中,所述第一初始化子单元将所述优化的神经网络子模型中的隐含层的各权值乘以预定的系数,作为所述普通卷积神经网络模型中的对应的隐含层的各权值。
- 一种电子设备,包括权利要求7-12的任一项所述的对神经网络模型进行训练的装置。
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2016/077975 WO2017166155A1 (zh) | 2016-03-31 | 2016-03-31 | 一种对神经网络模型进行训练的方法、装置及电子设备 |
| KR1020187017577A KR102161902B1 (ko) | 2016-03-31 | 2016-03-31 | 신경망 모델에 대한 훈련 방법, 장치 및 전자 장치 |
| JP2018539870A JP6601569B2 (ja) | 2016-03-31 | 2016-03-31 | ニューラルネットワークモデルの訓練方法、装置及び電子機器 |
| CN201680061886.8A CN108140144B (zh) | 2016-03-31 | 2016-03-31 | 一种对神经网络模型进行训练的方法、装置及电子设备 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2016/077975 WO2017166155A1 (zh) | 2016-03-31 | 2016-03-31 | 一种对神经网络模型进行训练的方法、装置及电子设备 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2017166155A1 true WO2017166155A1 (zh) | 2017-10-05 |
Family
ID=59962416
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2016/077975 Ceased WO2017166155A1 (zh) | 2016-03-31 | 2016-03-31 | 一种对神经网络模型进行训练的方法、装置及电子设备 |
Country Status (4)
| Country | Link |
|---|---|
| JP (1) | JP6601569B2 (zh) |
| KR (1) | KR102161902B1 (zh) |
| CN (1) | CN108140144B (zh) |
| WO (1) | WO2017166155A1 (zh) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109034367A (zh) * | 2018-08-22 | 2018-12-18 | 广州杰赛科技股份有限公司 | 神经网络更新方法、装置、计算机设备和可读存储介质 |
| CN109919308A (zh) * | 2017-12-13 | 2019-06-21 | 腾讯科技(深圳)有限公司 | 一种神经网络模型部署方法、预测方法及相关设备 |
| CN110738648A (zh) * | 2019-10-12 | 2020-01-31 | 山东浪潮人工智能研究院有限公司 | 一种基于多层卷积神经网络的相机外壳喷漆检测系统和方法 |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165738B (zh) * | 2018-09-19 | 2021-09-14 | 北京市商汤科技开发有限公司 | 神经网络模型的优化方法及装置、电子设备和存储介质 |
| US11556778B2 (en) * | 2018-12-07 | 2023-01-17 | Microsoft Technology Licensing, Llc | Automated generation of machine learning models |
| CN110288084A (zh) * | 2019-06-06 | 2019-09-27 | 北京小米智能科技有限公司 | 超网络训练方法和装置 |
| US11347308B2 (en) | 2019-07-26 | 2022-05-31 | Samsung Electronics Co., Ltd. | Method and apparatus with gaze tracking |
| KR102149495B1 (ko) * | 2019-08-19 | 2020-08-28 | 고려대학교 산학협력단 | 환경 예측 모델의 훈련지표 최적화 장치 및 그 동작방법 |
| CN112561026B (zh) * | 2019-09-25 | 2024-09-06 | 北京地平线机器人技术研发有限公司 | 神经网络模型的训练方法和装置、存储介质和电子设备 |
| WO2022035058A1 (en) | 2020-08-13 | 2022-02-17 | Samsung Electronics Co., Ltd. | Method and system of dnn modularization for optimal loading |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5452400A (en) * | 1991-08-30 | 1995-09-19 | Mitsubishi Denki Kabushiki Kaisha | Method of optimizing a combination using a neural network |
| CN104143327A (zh) * | 2013-07-10 | 2014-11-12 | 腾讯科技(深圳)有限公司 | 一种声学模型训练方法和装置 |
| WO2015054264A1 (en) * | 2013-10-08 | 2015-04-16 | Google Inc. | Methods and apparatus for reinforcement learning |
| CN104700153A (zh) * | 2014-12-05 | 2015-06-10 | 江南大学 | 基于模拟退火优化BP神经网络的pH值预测方法 |
| CN104794527A (zh) * | 2014-01-20 | 2015-07-22 | 富士通株式会社 | 基于卷积神经网络的分类模型构建方法和设备 |
| WO2015118686A1 (ja) * | 2014-02-10 | 2015-08-13 | 三菱電機株式会社 | 階層型ニューラルネットワーク装置、判別器学習方法および判別方法 |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002042107A (ja) * | 2000-07-31 | 2002-02-08 | Fuji Electric Co Ltd | ニューラルネットワークの学習方法 |
| CN100595780C (zh) * | 2007-12-13 | 2010-03-24 | 中国科学院合肥物质科学研究院 | 一种基于模块神经网络的手写体数字自动识别方法 |
| CN101975092B (zh) * | 2010-11-05 | 2012-08-15 | 中北大学 | 基于径向基函数神经网络集成的矿井瓦斯浓度中短期实时预测方法 |
| CN102479339B (zh) * | 2010-11-24 | 2014-07-16 | 香港理工大学 | 基于混合神经网络的风电场短期风速预测方法和系统 |
| JP6042274B2 (ja) * | 2013-06-28 | 2016-12-14 | 株式会社デンソーアイティーラボラトリ | ニューラルネットワーク最適化方法、ニューラルネットワーク最適化装置及びプログラム |
| CN104346622A (zh) * | 2013-07-31 | 2015-02-11 | 富士通株式会社 | 卷积神经网络分类器及其分类方法和训练方法 |
| CN104751228B (zh) * | 2013-12-31 | 2018-04-27 | 科大讯飞股份有限公司 | 用于语音识别的深度神经网络的构建方法及系统 |
| US10832138B2 (en) * | 2014-11-27 | 2020-11-10 | Samsung Electronics Co., Ltd. | Method and apparatus for extending neural network |
| CN104978601B (zh) * | 2015-06-26 | 2017-08-25 | 深圳市腾讯计算机系统有限公司 | 神经网络模型训练系统和方法 |
| CN105184312B (zh) * | 2015-08-24 | 2018-09-25 | 中国科学院自动化研究所 | 一种基于深度学习的文字检测方法及装置 |
-
2016
- 2016-03-31 CN CN201680061886.8A patent/CN108140144B/zh not_active Expired - Fee Related
- 2016-03-31 JP JP2018539870A patent/JP6601569B2/ja not_active Expired - Fee Related
- 2016-03-31 KR KR1020187017577A patent/KR102161902B1/ko not_active Expired - Fee Related
- 2016-03-31 WO PCT/CN2016/077975 patent/WO2017166155A1/zh not_active Ceased
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5452400A (en) * | 1991-08-30 | 1995-09-19 | Mitsubishi Denki Kabushiki Kaisha | Method of optimizing a combination using a neural network |
| CN104143327A (zh) * | 2013-07-10 | 2014-11-12 | 腾讯科技(深圳)有限公司 | 一种声学模型训练方法和装置 |
| WO2015054264A1 (en) * | 2013-10-08 | 2015-04-16 | Google Inc. | Methods and apparatus for reinforcement learning |
| CN104794527A (zh) * | 2014-01-20 | 2015-07-22 | 富士通株式会社 | 基于卷积神经网络的分类模型构建方法和设备 |
| WO2015118686A1 (ja) * | 2014-02-10 | 2015-08-13 | 三菱電機株式会社 | 階層型ニューラルネットワーク装置、判別器学習方法および判別方法 |
| CN104700153A (zh) * | 2014-12-05 | 2015-06-10 | 江南大学 | 基于模拟退火优化BP神经网络的pH值预测方法 |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919308A (zh) * | 2017-12-13 | 2019-06-21 | 腾讯科技(深圳)有限公司 | 一种神经网络模型部署方法、预测方法及相关设备 |
| CN109919308B (zh) * | 2017-12-13 | 2022-11-11 | 腾讯科技(深圳)有限公司 | 一种神经网络模型部署方法、预测方法及相关设备 |
| CN109034367A (zh) * | 2018-08-22 | 2018-12-18 | 广州杰赛科技股份有限公司 | 神经网络更新方法、装置、计算机设备和可读存储介质 |
| CN110738648A (zh) * | 2019-10-12 | 2020-01-31 | 山东浪潮人工智能研究院有限公司 | 一种基于多层卷积神经网络的相机外壳喷漆检测系统和方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| KR20180084969A (ko) | 2018-07-25 |
| JP2019508803A (ja) | 2019-03-28 |
| KR102161902B1 (ko) | 2020-10-05 |
| CN108140144A (zh) | 2018-06-08 |
| JP6601569B2 (ja) | 2019-11-06 |
| CN108140144B (zh) | 2021-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017166155A1 (zh) | 一种对神经网络模型进行训练的方法、装置及电子设备 | |
| JP7376731B2 (ja) | 画像認識モデル生成方法、装置、コンピュータ機器及び記憶媒体 | |
| CN108764195B (zh) | 手写模型训练方法、手写字识别方法、装置、设备及介质 | |
| US20220083868A1 (en) | Neural network training method and apparatus, and electronic device | |
| CN108009594B (zh) | 一种基于变分组卷积的图像识别方法 | |
| CN114677535A (zh) | 域适应图像分类网络的训练方法、图像分类方法及装置 | |
| CN113822434A (zh) | 用于知识蒸馏的模型选择学习 | |
| CN111860840B (zh) | 深度学习模型训练方法、装置、计算机设备及存储介质 | |
| CN111310821B (zh) | 多视图特征融合方法、系统、计算机设备及存储介质 | |
| CN114565625B (zh) | 一种基于全局特征的矿物图像分割方法及装置 | |
| WO2022166797A1 (zh) | 图像生成模型的训练方法、生成方法、装置及设备 | |
| CN112686320A (zh) | 图像分类方法、装置、计算机设备及存储介质 | |
| CN112116009A (zh) | 基于卷积神经网络的新冠肺炎x射线图像识别方法及系统 | |
| CN110533610A (zh) | 图像增强模型的生成方法及装置、应用方法及装置 | |
| CN115511051A (zh) | 一种基于权重注意力提升卷积神经网络性能的方法 | |
| CN112819157B (zh) | 神经网络训练的方法及装置、智能行驶控制的方法及装置 | |
| CN110506280B (zh) | 神经网络训练系统、方法和计算机可读存储介质 | |
| CN115049717B (zh) | 一种深度估计方法及装置 | |
| CN107229613B (zh) | 一种基于向量空间模型的英汉语料提取方法 | |
| CN107564013B (zh) | 融合局部信息的场景分割修正方法与系统 | |
| CN109389215B (zh) | 一种深度学习网络的网络结构确定方法及装置 | |
| CN114360003A (zh) | 一种人脸表情识别方法及装置 | |
| CN114548355A (zh) | Cnn训练方法、电子设备和计算机可读存储介质 | |
| CN116245745B (zh) | 图像处理方法及图像处理设备 | |
| CN108734222B (zh) | 基于校对网络的卷积神经网络图像分类方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| ENP | Entry into the national phase |
Ref document number: 20187017577 Country of ref document: KR Kind code of ref document: A |
|
| ENP | Entry into the national phase |
Ref document number: 2018539870 Country of ref document: JP Kind code of ref document: A |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16895936 Country of ref document: EP Kind code of ref document: A1 |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 16895936 Country of ref document: EP Kind code of ref document: A1 |

