CN112270406B - Nerve information visualization method of brain-like computer operating system - Google Patents
Nerve information visualization method of brain-like computer operating system Download PDFInfo
- Publication number
- CN112270406B CN112270406B CN202011255463.4A CN202011255463A CN112270406B CN 112270406 B CN112270406 B CN 112270406B CN 202011255463 A CN202011255463 A CN 202011255463A CN 112270406 B CN112270406 B CN 112270406B
- Authority
- CN
- China
- Prior art keywords
- neuron
- nodes
- node
- layer
- importance
- 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.)
- Active
Links
- 238000007794 visualization technique Methods 0.000 title abstract description 12
- 210000005036 nerve Anatomy 0.000 title abstract description 6
- 210000002569 neuron Anatomy 0.000 claims abstract description 156
- 238000013528 artificial neural network Methods 0.000 claims abstract description 42
- 230000001537 neural effect Effects 0.000 claims abstract description 22
- 238000012800 visualization Methods 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 12
- 239000003086 colorant Substances 0.000 claims abstract description 8
- 230000002776 aggregation Effects 0.000 claims abstract description 6
- 238000004220 aggregation Methods 0.000 claims abstract description 6
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims 1
- 238000013527 convolutional neural network Methods 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012421 spiking Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a neural information visualization method of a brain-like computer operating system, which comprises the following steps: obtaining a connection description file of a pulse neural network, and carrying out global coding on each layer of neuron nodes according to the connection description file, wherein each neuron node obtains a global unique identifier, each layer of neuron nodes are represented in an aggregation mode and are distinguished by different colors, and the connection relation of the neuron nodes between adjacent layers is represented by a connecting edge and is distinguished by different colors; and calculating the importance of each neuron node according to the number of the edges and the weight of the edges of the neuron nodes, and selecting the neuron nodes according to the importance to visualize. The method solves the problems that the connection description files are more, the number of the neuron nodes is more, and the connection lines among the neuron nodes are more and are not easy to distinguish. The reasonable visualization of the nerve information of the brain-like computer operating system is realized, and the understanding of the working process of the impulse neural network is facilitated.
Description
Technical Field
The invention belongs to the technical field of novel computers, and particularly relates to a neural information visualization method of a brain-like computer operating system.
Background
Deep learning has received high attention from scientific research institutions and industry after 2006, has developed greatly in various fields such as images and voices, and has comprehensively exceeded traditional algorithms in various fields. Impulse neural networks (SNN-Spiking Neuron Networks) are often known as third generation artificial neural networks. The first generation of neural networks were perceptrons, which were a simple model of neurons and were only capable of processing binary data. The second generation neural network comprises a relatively wide range of BP neural networks. And the impulse neural network is more similar to the actual connection relation and behavior of the brain neurons.
Currently, the tools disclosed on the network for visualizing the convolutional neural network structure are more, and mainly comprise: 1) Netscope: the model definition file is used as input to obtain a visual structure diagram of the neural network, which is a visual neural network topology tool based on a webpage and only supports a cafe deep learning framework of the primary cler division of the university of california. 2) ConvNetDraw: the visual command is used as input, and the visual output neural network model structure is also a web-based tool. The model of the structural block is used for displaying, and the three-dimensional proportion adjustment can be carried out on the structural block, so that the model is very visual. 3) Netron: the visual structure diagram of the neural network is obtained by taking a model definition file and a model weight file (which can be defaults) as inputs, is based on a webpage, and can support a main stream deep learning framework such as ONNX, keras, coreML, tensorFlow, caffe, MXNET by using js and python.
Cao Lihong of China media university in publication No. CN106372721A discloses a method for visualizing a large-scale neural network in a 3D form, and the structure of the neural network is shown in the 3D form; chunfang et al, published patent application number CN107392085A, of Shanghai institute of precision metrology, disclose a method for visualizing convolutional neural networks, which can be well shown to facilitate understanding of convolutional neural networks, for exploring superiority of convolutional neural networks; the patent application with publication number of CN110782031A in Beijing computer technology and application research discloses a multi-frame convolutional neural network model structure visualization and network reconstruction method, which can intuitively modify different layers to realize network reconstruction and can change the neural network attribute and update and display in real time.
Because of the complexity of the impulse neural network structure of the brain-like computer operating system, the problems of more connection description files, more neuron nodes and more connection lines among the neuron nodes are difficult to distinguish when the impulse neural network structure of the brain-like computer operating system is visualized. Therefore, all the above visualization methods are not applicable to the visualization of the impulse neural network structure of the brain-like computer operating system.
Disclosure of Invention
The invention aims to provide a neural information visualization method of a brain-like computer operating system, which aims to solve the problems that the connection description files are more, the number of neuron nodes is more, and the connection lines among the neuron nodes are more and are not easy to distinguish.
In order to achieve the above object, the present invention provides the following technical solutions:
a neural information visualization method of a brain-like computer operating system comprises the following steps:
obtaining a connection description file of a pulse neural network, and carrying out global coding on each layer of neuron nodes according to the connection description file, wherein each neuron node obtains a global unique identifier, each layer of neuron nodes are represented in an aggregation mode and are distinguished by different colors, and the connection relation of the neuron nodes between adjacent layers is represented by a connecting edge and is distinguished by different colors;
and calculating the importance of each neuron node according to the number of the edges and the weight of the edges of the neuron nodes, and selecting the neuron nodes according to the importance to visualize.
Preferably, all the neuron nodes in the same layer of the impulse neural network are represented in an aggregation mode, and the aggregation representations of the neuron nodes in two adjacent layers are also in adjacent positions by adopting the same color representation, so that the connection relation representation between the neuron nodes in two adjacent layers is convenient.
Preferably, each layer of neuron nodes is aggregated into a geometric shape for representation. The geometric shapes can be round, elliptic and other smooth geometric shapes without edges and corners, and can also be matrix, triangle and other geometric shapes with edges and corners.
Preferably, all the connection relations between two layers of neuron nodes are represented by the same color continuous edges. In order to improve visual clarity, the color of the neuron node is different from the corresponding border color.
Preferably, when the neural information visualization is performed, the neuron information layout is stored in a data structure, wherein the data structure comprises a data unit, a connection relation unit and a layer unit, and the data unit is used for storing a globally unique identifier of a neuron node, a visualized position coordinate and a layer level; the connection relation unit is used for storing two neuron nodes and the visualized color of the connecting edge between the two neuron nodes; the layer unit is used for storing the hierarchy name.
Since the number of the neuron nodes is large, whether a certain neuron is displayed is selected according to the number of the edges of the neuron nodes and other neurons and the edge weight. If the neuron nodes are too much sampled, the visualized neuron nodes are too dense, and the connection relation among the neuron nodes cannot be seen; if the sampling of the neuron nodes is too small, the main information is lost, and the main structure of the impulse neural network cannot be observed. In order to reasonably sparse sample neurons, the importance of the neuron nodes needs to be calculated and ordered. Preferably, the importance of each neuron node is calculated using the following formula:
wherein ,
representing the ith neuron node i Is the absolute importance of the neuron before regularization, inNum represents the degree of entry of the neuron node, w 1 Is the degree of entry coefficient of the neuron node, outNum represents the degree of exit of the neuron node, w 2 Is the coefficient of the degree of departure of the neuron node, weight represents the sum of the absolute values of the edge weights of the neuron node, and w 3 Is the weighting coefficient of the neuron node, +.>
Is the importance of the final neuron node, < +.>
Representing the jth neuron node j Is the absolute importance of the neurons before regularization, n represents the total number of neuron nodes. Wherein, the number of the connecting edges of the current neuron node is accessedAnd taking the number of the connected edges connected with the current neuron node as the output degree of the current neuron node as the input degree of the current neuron node.
Preferably, when selecting the neuron nodes for visualization according to the importance, an importance threshold is set, and the neuron nodes with importance greater than the importance threshold are screened for visualization. So that the more edges the neuron node is connected to, the greater the absolute value of the weight of the edge is preserved preferentially.
Compared with the prior art, the invention has the beneficial effects that at least the following steps are included:
the nerve information visualization method of the brain-like computer operating system solves the problem of more connection description files by carrying out global coding on neurons, screens and visualizes the neurons according to the importance of the nodes of the neurons, solves the problem of more display difficulties of the nodes of the neurons by adopting the sparsification processing method, simultaneously expresses the connection relationship in a connecting edge form and distinguishes the connection relationship by adopting different colors, and solves the problem of more connection lines between the nodes of the neurons which are not easy to distinguish. The reasonable visualization of the nerve information of the brain-like computer operating system is realized, and the understanding of the working process of the impulse neural network is facilitated.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for visualizing neural information of a brain-like computer operating system provided by an embodiment of the present invention;
FIG. 2 is an internal data structure of a connection description file of a impulse neural network according to an embodiment of the present invention;
FIG. 3 is an internal data structure of an intermediate json file for visualization of neural information provided by an embodiment of the present invention;
FIG. 4 is a quadruple within the data field of a json file provided by an embodiment of the present invention;
FIG. 5 is a triplet within the json file links field provided by an embodiment of the present invention;
fig. 6 is a neural information visualization diagram of an electroencephalogram simulated impulse neural network provided by an embodiment of the invention;
fig. 7 is a neural information visualization of a memory model impulse neural network according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the detailed description is presented by way of example only and is not intended to limit the scope of the invention.
In the process of carrying out neural information visualization on a pulse neural network of a brain-like computer operating system of a Darwin No. 2 neural mimicry chip of Zhejiang university, the problems of more connection description files, more neuron nodes and more connection lines among the neuron nodes are encountered. In order to solve the problem that the neural information visualization is difficult due to the problems, the embodiment of the invention provides a neural information visualization method of a brain-like computer operating system, which is used for carrying out the neural information visualization based on a pulse neural network model connection description file of the brain-like computer operating system of a Darwin No. 2 neural mimicry chip.
Fig. 1 is a flowchart of a neural information visualization method of a brain-like computer operating system according to an embodiment of the present invention. As shown in fig. 1, the neural information visualization method includes the steps of:
and step 1, reading the connection description file of the impulse neural network according to the connection relation between the impulse neural network layers and the order from the input layer to the output layer.
The connection description file of the impulse neural network describes the impulse neural network neurons and the connection relationship between the neurons. The impulse neural network has a plurality of connection description files, and each file describes the connection relation between two layers of neurons. Fig. 2 is an internal data structure of a connection description file of the impulse neural network. As shown in fig. 2, each row of the connection description file is a quadruple, the first field of the quadruple is the number in the starting neuron layer, i.e. the number of the starting neuron in the starting layer, the second field is the number in the target neuron layer, i.e. the number of the target neuron in the target layer, the third field is a weight, i.e. the weight of the processing input value of the neuron, which is an inherent property of the neuron's continuous edge, and the fourth field is the pulse delay, i.e. the delay of the pulse signal from the starting neuron to the target neuron.
And 2, renumbering the nerve cell nodes of each layer according to the read pulse nerve network connection description file, converting the layer numbering into a global unique identifier, and simultaneously determining the color of each layer of nerve cell to form the attribute of the nerve cell.
And 3, generating a triplet (an initial neuron number, a target neuron number and a color of an edge) describing the node connection relation according to the connection description file and the self attribute of the neuron node, wherein the color of the edge is determined according to the layer where the edge connection neuron is located.
And 4, laying out the neuron nodes according to the connection relation among the neurons of the impulse neural network, wherein the neuron nodes of the same layer are gathered and placed in the same area, and the neurons of the adjacent layers are gathered and placed in adjacent positions.
And 5, selecting whether to display a certain neuron or not according to the number of the edges and the weight of the edges of the neuron and other neurons.
Because the number of the neuron nodes and the connecting lines in the original impulse neural network is excessive, if all the nodes and the connecting lines are displayed together, the key structure of the impulse neural network cannot be displayed, and therefore the impulse neural network needs to be sparsely displayed. If the neurons are too sampled, the visualized neurons are too dense, and the connection relation among the neurons cannot be seen; if the neurons are sampled too little, the main information is lost, and the main structure of the impulse neural network cannot be observed. The method is characterized in that the importance of the neurons is calculated according to the number of the edges and the weight of the edges of the neurons and other neurons, the neurons are ordered according to the importance, and the neurons with the greater importance are preferentially reserved.
The formula for the importance of neurons is as follows:
after the importance of the neurons is calculated, an importance threshold e (e (0, 1)) is set to control which neurons are displayed, neurons with importance greater than the threshold are displayed, and neurons smaller than the threshold are hidden.
And 6, deriving a json file describing the neuron layout and the colors of the edges, and visualizing the derived json file by using echartists.
In an embodiment, the json file is generated using python code and visualized using the graph type of echorts. Fig. 3 is a data structure of a json file, which contains three fields: data unit data, link and layer unit links. The data field is an array, each element in the data field is a quadruple, and the quadruple contains a key value name, a position coordinate (x, y) and belonging layer information of a neuron node, as shown in fig. 4. The links field is also an array, each element in the array is a triplet, and the triplet includes a key value source of a starting neuron node, a key value target of a target neuron, and a color linetype of a connection line, as shown in fig. 5.
The result of visualizing the neural information of the electroencephalogram simulated impulse neural network and the memory model impulse neural network by using the neural information visualization method of the brain-like computer operating system is shown in fig. 6 and 7, and the structure of the impulse neural network is clearly shown in the drawings, namely, the connection relationship between the neuron nodes of the impulse neural network and each neuron node is shown.
The foregoing detailed description of the preferred embodiments and advantages of the invention will be appreciated that the foregoing description is merely illustrative of the presently preferred embodiments of the invention, and that no changes, additions, substitutions and equivalents of those embodiments are intended to be included within the scope of the invention.
Claims (3)
1. A method for visualizing neural information of a brain-like computer operating system, comprising the steps of:
step 1, obtaining a connection description file of a pulse neural network, wherein each row of the connection description file is a quadruple, a first field of the quadruple is a serial number in a starting neuron layer, a second field of the quadruple is a serial number in a target neuron layer, a third field of the quadruple is a weight, the weight is an inherent attribute of a neuron connecting edge, and a fourth field of the quadruple is pulse delay;
step 2, carrying out global coding on each layer of neuron nodes according to the connection description file, wherein each neuron node obtains a global unique identifier, and simultaneously determining the color of each layer of neurons to form the self attribute of the neurons;
step 3, generating a triplet (initial neuron number, target neuron number, edge color) describing the node connection relation according to the connection description file and the self attribute of the neuron node, wherein the edge color is determined according to the layer where the edge connection neuron is located;
step 4, laying out the neuron nodes according to the connection relation among the neurons of the impulse neural network, wherein the neuron nodes of each layer are represented in an aggregation mode and are distinguished by different colors, the neuron nodes of the same layer are placed in the same area in an aggregation mode and are represented in a geometric shape, the neuron nodes of the adjacent layer are placed in adjacent positions, the connection relation among the neuron nodes of the two adjacent layers is represented conveniently, and the connection relation among the neuron nodes of the adjacent layers is represented by a connecting edge and is distinguished by different colors;
and 5, calculating the importance of each neuron node according to the number of the connected edges and the weight of the connected edges of the neuron nodes, setting an importance threshold value, and screening the neuron nodes with the importance larger than the importance threshold value for visualization, wherein the importance of each neuron node is calculated by adopting the following formula:
wherein ,
representing the ith neuron node i Is the absolute importance of the neuron before regularization, inNum represents the degree of entry of the neuron node, w 1 Is the degree of entry coefficient of the neuron node, outNum represents the degree of exit of the neuron node, w 2 Is the coefficient of the degree of departure of the neuron node, weight represents the sum of the absolute values of the edge weights of the neuron node, and w 3 Is the weighting coefficient of the neuron node, +.>
Is the importance of the final neuron node, < +.>
Representing the jth neuron node j The absolute importance of the neurons before regularization, n represents the total number of neuron nodes;
the neuron information layout is stored in a data structure, and the data structure comprises a data unit, a connection relation unit and a layer unit, wherein the data unit is used for storing a globally unique identifier of a neuron node, a visual position coordinate and a hierarchy; the connection relation unit is used for storing two neuron nodes and the visualized color of the connecting edge between the two neuron nodes; the layer unit is used for storing the hierarchy name.
2. The method for visualizing neural information for a brain-like computer operating system of claim 1, wherein all connections between two layers of neuron nodes are represented by the same color of edges.
3. The method for visualizing neural information for a brain-like computer operating system of claim 1, wherein the color of the neuron nodes is different from its corresponding border color.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011255463.4A CN112270406B (en) | 2020-11-11 | 2020-11-11 | Nerve information visualization method of brain-like computer operating system |
| PCT/CN2020/128463 WO2022099557A1 (en) | 2020-11-11 | 2020-11-12 | Neuron information visualization method for operating system of brain-like computer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011255463.4A CN112270406B (en) | 2020-11-11 | 2020-11-11 | Nerve information visualization method of brain-like computer operating system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112270406A CN112270406A (en) | 2021-01-26 |
| CN112270406B true CN112270406B (en) | 2023-05-23 |
Family
ID=74340656
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011255463.4A Active CN112270406B (en) | 2020-11-11 | 2020-11-11 | Nerve information visualization method of brain-like computer operating system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112270406B (en) |
| WO (1) | WO2022099557A1 (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819160B (en) * | 2021-02-24 | 2023-10-31 | 文远鄂行(湖北)出行科技有限公司 | Visualization method, device and equipment for neural network model and storage medium |
| CN112561043B (en) * | 2021-03-01 | 2021-06-29 | 浙江大学 | Neural model splitting method of brain-like computer operating system |
| CN112561042B (en) * | 2021-03-01 | 2021-06-29 | 浙江大学 | Neural model mapping method of brain-like computer operating system |
| CN113297314B (en) * | 2021-07-28 | 2021-11-02 | 深圳市永达电子信息股份有限公司 | Data visualization method and device and storage medium |
| CN113791913B (en) * | 2021-11-16 | 2022-02-11 | 浙江大学 | Task migration method of brain-like computer operating system |
| CN114399033B (en) * | 2022-03-25 | 2022-07-19 | 浙江大学 | Brain-like computing system and method based on neuron instruction coding |
| CN114611686B (en) * | 2022-05-12 | 2022-08-30 | 之江实验室 | Synapse delay implementation system and method based on programmable neural mimicry core |
| CN115879544B (en) * | 2023-02-28 | 2023-06-16 | 中国电子科技南湖研究院 | Neuron coding method and system for distributed brain-like simulation |
Family Cites Families (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6452612B2 (en) * | 2012-11-13 | 2019-01-16 | エルミンダ リミテッド | System for analyzing neurophysiological data, method for constructing a database from neurophysiological data, computer-readable medium |
| US10055434B2 (en) * | 2013-10-16 | 2018-08-21 | University Of Tennessee Research Foundation | Method and apparatus for providing random selection and long-term potentiation and depression in an artificial network |
| WO2016150472A1 (en) * | 2015-03-20 | 2016-09-29 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Relevance score assignment for artificial neural network |
| EP3304261A4 (en) * | 2015-05-26 | 2019-02-06 | Ayasdi Inc. | Outcome analysis for graph generation |
| CN105788608B (en) * | 2016-03-03 | 2019-03-26 | 渤海大学 | Chinese phonetic mother method for visualizing neural network based |
| US11086471B2 (en) * | 2016-06-06 | 2021-08-10 | Salesforce.Com, Inc. | Visualizing neural networks |
| CN106372721B (en) * | 2016-08-29 | 2018-08-21 | 中国传媒大学 | The 3D method for visualizing of Large Scale Neural Networks |
| CN106650922B (en) * | 2016-09-29 | 2019-05-03 | 清华大学 | Hardware neural network conversion method, computing device, software and hardware cooperative system |
| US11544539B2 (en) * | 2016-09-29 | 2023-01-03 | Tsinghua University | Hardware neural network conversion method, computing device, compiling method and neural network software and hardware collaboration system |
| US20190005384A1 (en) * | 2017-06-29 | 2019-01-03 | General Electric Company | Topology aware graph neural nets |
| US10366322B2 (en) * | 2017-10-06 | 2019-07-30 | DeepCube LTD. | System and method for compact and efficient sparse neural networks |
| CN107704925B (en) * | 2017-10-16 | 2020-04-14 | 清华大学 | Visual analysis system and method for deep neural network training process |
| CN110322010B (en) * | 2019-07-02 | 2021-06-25 | 深圳忆海原识科技有限公司 | Pulse neural network operation system and method for brain-like intelligence and cognitive computation |
| CN110782031A (en) * | 2019-09-27 | 2020-02-11 | 北京计算机技术及应用研究所 | Multi-frame convolutional neural network model structure visualization and network reconstruction method |
| CN110781933B (en) * | 2019-10-14 | 2022-08-05 | 杭州电子科技大学 | Visual analysis method for understanding graph convolution neural network |
| CN111082949B (en) * | 2019-10-29 | 2022-01-28 | 广东工业大学 | Method for efficiently transmitting pulse data packets in brain-like computer |
| CN110909869B (en) * | 2019-11-21 | 2022-08-23 | 浙江大学 | Brain-like computing chip based on impulse neural network |
| CN111291243B (en) * | 2019-12-30 | 2022-07-12 | 浙江大学 | Visual reasoning method for uncertainty of spatiotemporal information of character event |
| CN111797333B (en) * | 2020-06-04 | 2021-04-20 | 南京擎盾信息科技有限公司 | Public opinion spreading task display method and device |
-
2020
- 2020-11-11 CN CN202011255463.4A patent/CN112270406B/en active Active
- 2020-11-12 WO PCT/CN2020/128463 patent/WO2022099557A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022099557A1 (en) | 2022-05-19 |
| CN112270406A (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112270406B (en) | Nerve information visualization method of brain-like computer operating system | |
| Zhou et al. | Edge bundling in information visualization | |
| Gyulassy et al. | Efficient computation of Morse-Smale complexes for three-dimensional scalar functions | |
| Batagelj et al. | Visual analysis of large graphs using (x, y)-clustering and hybrid visualizations | |
| CN109919097A (en) | Face and key point combined detection system, method based on multi-task learning | |
| CN113052955B (en) | Point cloud completion method, system and application | |
| CN107610221B (en) | Three-dimensional model generation method based on isomorphic model representation | |
| CN115601511B (en) | Three-dimensional reconstruction method and device, computer equipment and computer readable storage medium | |
| Villalba-Diez et al. | Lean dendrochronology: Complexity reduction by representation of kpi dynamics looking at strategic organizational design | |
| Zhang et al. | Machine learning aided 2D-3D architectural form finding at high resolution | |
| CN109255004A (en) | The online interaction formula method for visualizing of accuracy guarantee towards geographical spatial data | |
| Steed et al. | Web-based visual analytics for extreme scale climate science | |
| CN104778308B (en) | The recognition methods of aircaft configuration section bar and device | |
| CN109063223A (en) | The light weight method and device of BIM model and the processing method and system of BIM model | |
| Lai et al. | Small blend suppression from B-rep models in computer-aided engineering analysis | |
| Liu et al. | Visualizing events in time-varying scientific data | |
| CN114092641A (en) | Method, device and equipment for generating wiring board drawing and readable storage medium | |
| CN113593007A (en) | Single-view three-dimensional point cloud reconstruction method and system based on variational self-coding | |
| Saravanan et al. | An intelligent constitutive and collaborative framework by integrating the design, inspection and testing activities using a cloud platform | |
| Liu et al. | 3D Deep Learning for 3D Printing of Tooth Model | |
| Peng et al. | Dmnevis: a novel visual approach to explore evolution of dynamic multivariate network | |
| CN111309917A (en) | Super-large scale academic network visualization method and system based on conference periodical galaxy diagram | |
| US20240028787A1 (en) | Techniques for design space exploration in a multi-user collaboration system | |
| Su et al. | A multi-level visualization method for IT system structure | |
| Zhang et al. | Application analysis of particle swarm optimization convolutional neural network in industrial design |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |