CN106845541A - A kind of image-recognizing method based on biological vision and precision pulse driving neutral net - Google Patents
A kind of image-recognizing method based on biological vision and precision pulse driving neutral net Download PDFInfo
- Publication number
- CN106845541A CN106845541A CN201710036419.6A CN201710036419A CN106845541A CN 106845541 A CN106845541 A CN 106845541A CN 201710036419 A CN201710036419 A CN 201710036419A CN 106845541 A CN106845541 A CN 106845541A
- Authority
- CN
- China
- Prior art keywords
- image
- sigma
- pulse
- value
- gabor
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention proposes a kind of image-recognizing method based on biological vision and precision pulse driving neutral net.The present invention is inspired by biological vision hierarchical system, in the characteristic extraction part of image, using the cell operating mechanism of HMAX modeling receptive fields, first with the marginal information of Gabor filtering reinforcing images, max pooling treatment is carried out to the image by the filtered all directions of Gabor again, the purpose for extracting topmost feature and dimension-reduction treatment is reached.In character image data processing method, phase coding technology is selected, the Pixel Information of image has been converted into pulse phenomenon, so not only allowed for the spatial information of image, it is also contemplated that the temporal information of image.The present invention has certain biological basis, and with good feasibility and robustness, and it for the identification and classification of image, especially the accuracy in noise image is greatly improved.
Description
Technical field
The present invention relates to pattern-recognition and class brain calculating field, and in particular to one kind is driven based on biological vision with precision pulse
The image-recognizing method of dynamic neutral net.
Background technology
Pattern-recognition is one of topic most hot at present of artificial intelligence field, and its target is entered by the image for gathering
Certain treatment is gone to obtain the relevant information of target scene.But Chinese Academy of Sciences Tan car pusher academician is in 2016 Chinese artificial intelligence conferences
Pointed out on (CCAI 2016):General PRS is shouldered heavy responsibilities --- and its Main Bottleneck is robustness, adaptivity
With can three aspects of generalization.These technical barriers cause that the development of pattern-recognition cannot adapt to the need of society and Vehicles Collected from Market
Ask.
And class brain calculates the brain for not only simulating people, and Other subjects are combined, including signal transacting science, meter
Calculation machine technology, statistics, physics, applied mathematics, cognitive science are refreshing and through physiology etc., cause national governments and research aircraft
The extensive concern of structure, and have great breakthrough in terms of three big bottleneck problems of pattern-recognition.USA and EU is also thrown this
Enter huge fund, be successively proposed respective human brain project:" human brain plan " (the Human Brain in the U.S.
Project) it is devoted to exploring neuron, the relation between neural circuit and cerebral function, " the brain work of European Union from neuron aspect
It is whole that cardon spectrum plan " (Brain Activity Map Project, or Brain Initiative) is then devoted to simulation
Human brain.
Impulsive neural networks be class brain calculating field expert and scholar propose third generation neutral net, its with based on arteries and veins
The traditional artificial neural network for rushing frequency coding information is compared, and possesses more powerful computing capability, can simulate various nerve letters
Number and arbitrary continuous function, be especially suitable for realizing the process problem of cerebral nerve signal, be to carry out complicated space time information treatment
Effective tool.Although currently the research of the PRS based on impulsive neural networks of correspondence technical barrier has just just risen
Step, document both domestic and external is not a lot, but scholars have begun to propose the fruitful and full recommendation method of innovation.And
And the research based on neural network filter theory is considered as always the most successful one side of Application of Neural Network, it
Development be can be described as with neural network theory it is complementary, and in nearly all existing impulsive neural networks physical model
All it is successfully applied in area of pattern recognition.Impulsive neural networks theory makes progress can be to the hair of pattern recognition theory
Exhibition brings inspiration;Conversely, the progress of pattern recognition theory again can driving pulse neural network theory significantly long-run development.
The content of the invention
The main purpose of the present invention be for present mode identifying system robustness, adaptivity and can generalization three
Big bottleneck, builds an image-recognizing method for driving neutral net with precision pulse based on biological vision.To different figures
Picture is pre-processed, including image characteristics extraction, during Object representation, human vision hierarchical system is simulated, using HMAX
Model realization is operated;The input of pulse is converted thereof into according to the view data that obtains afterwards, consequently facilitating follow-up based on class
The treatment that brain is calculated;Categorised decision is carried out finally by impulsive neural networks learning algorithm.Its particular content is as follows:
The feature extraction of 1 biological vision system
In order to improve the practicality of object identification, a kind of vision layered system is employed, for the extraction of characteristics of image.
HMAX models and traditional SR (Sparse Repesentaiton, rarefaction representation) are compared, and can preferably describe the entirety of data
Structure, so as in the data problem of such as image characteristics extraction etc, there is obvious advantage.
1.1 S1 layers of Gabor filtering process
S1 layers representative be in visual cortex receptive field (Receptive Field) simple cell treatment picture signal
Mode.When the V1 areas simple cell of receptive field carries out the matching of unit, feature is extracted using the higher order filter of sparse coding.Perhaps
Many researchers establish the computation model of sparse coding using two-dimensional Gabor filter function.The general type of sparse coding
It is:
SC=AH
Wherein sci, ai, hjIt is sparse piece of element of SC of unit, A is the basic function of sparse coding, and H is sparse.A's
The most frequently used expression-form is:
||·||fIt is Frobenius normal forms, μ is normal number.Gabor respond G (x, y) can be approximate be converted into it is sparse
The form of coding:
G (x, y)=S (x, y) K (x, y),
Wherein S (x, y) represents complicated sine functions, and its span is [- 1,1], therefore meets above-mentioned basic function A
Form.K (x, y) is the envelope function of two-dimensional discrete Gauss equation, and λ represents wavelength, and its value is no more than image length and width
1/5。It is phase offset, at [- 180 °, 180 °], γ represents length-width ratio to value, determines that image is filtered by Gabor
Shape.σ depends on bandwidth b:
For simplicity the real part part filtered using Gabor is learnt to characteristics of image:
X'=x cos θ+y sin θs, y'=-x sin θ+y cos θ
In the present invention, offset phase is set respectivelyWavelength X and bandwidth b are 0 °, 10 and 1, therefore σ=0.56 λ.
In S1 layers, the Gabor filtering of (0 °, 45 °, 90 °, 135 °) four direction is chosen, and its result is normalized to
[-1,1]。
1.2 C1 layers of maximum pond treatment
Image enhances its marginal information after S1 layers, carries out extraction and the dimensionality reduction of feature using maximum pond at C1 layers,
It embodies as follows:
Wherein m is the size of the sliding window in maximum pond.
2 pulse codes
In the present invention, selected phase encryption algorithm (a kind of time encoding scheme) produces pulse train.Coding unit
Structure be made up of three parts:Positive neuron (POS), negative neurons (NEG), output neuron (EOUT).Entirely compiling
During code, each incoming spiking represents a neuron activity, is connected to a receptive field region, i.e., one volume
Code unit is connected to a pixel.Subthreshold membrane potential oscillation (SMOS) is also related to action potential, and each pixel is strong in RF
Angle value is converted into a rectilinear oscillation for the time action potential for processing meticulously, and this is described as cosine function:
WhereinIt is i-th concussion function of encoding nerve unit, in periodically;A is amplitude, and ω represents angular speed, φ0
It is initial phase, i-th offset phase φ of encoding nerve unitiComputing formula be:
φi=φ0+(i-1)·Δφ
Wherein Δ φ is minimum offset identity, and its value is 2 π/n, and n is the number of neuron.Concussion cycle t is setmaxFor
200ms.Each pixel of image is represented with for example following formula of the relation of time:
Wherein xiThe pixel value of representative image ith pixel.When the incoming coding layer of pixel, will cause upwardly or downwardly
Film vibration, if film potential exceed threshold value, stimulate produce.The product of pulse train can be controlled by adjusting amplitude and threshold value
It is raw.
3 impulsive neural networks learn
Impulsive neural networks mainly learn to the pulse train that image is produced, and pulse train is represented by:
Wherein, tfF-th pulse Time Of Release is represented, δ (x) represents Dirac delta functions, at that time x=0, δ (x)=
1, otherwise δ (x)=0.The present invention uses the supervised learning algorithm of impulsive neural networks, the purpose is to:It is multiple defeated for what is given
Enter pulse train Si(t) and multiple target pulse sequence SdT (), finds the suitable synaptic weight matrix w of impulsive neural networks, make
The output pulse sequence S of neurono(t) and corresponding target pulse sequence SdT () is as close possible to i.e. both error assessment
Functional value is minimum.
Precise-spike-driven synaptic plasticity (PSD) utilize precise time pulse coded information
Pulse train to image learns, and its basis is leaky integrate-and-fire models.When using this study
During rule adjustment weight, postsynaptic potential (PSP) is the summation of the weight of the afferent nerve of all input pulses:
Wherein ωiAnd tiIt is respectively synapse weight and the duration of ignition of i & lt input, VrestIt is reset voltage.K is double fingers
The kernel function of number form formula:
Wherein tfIt is i-th f-th pulse of neuron generation;V0It is normalized parameter, it makes the value of K be not more than 1;
τsExpression slow-decay constant, and τfRefer to rapid decay constant, make τs/τf=4.Postsynaptic currents be PSD rule in one it is important
Parameter, it meets following formula:
WhereinIt is the synaptic currents of i & lt input;H (x) is Heaviside functions, works as x<Its value is 0 when 0, works as x=
Its value is 0.5 when 0, works as x>Its value is 1 when 0.Widrow-Hoff rule synapse weight Changing Pattern be:
And weight change can be typically expressed as:
PSD rules change the inspiration that synapse weight receives Widrow-Hoff rules, and its form is:
In the study stage, the step-length of impulsive neural networks is set to 100 times.
4 discriminant classifications
Image sequence by after PSD rule learnings, set of pulses output sequence can be produced, using van Rossum
Metric carries out discriminant classification to result.This method depends on the distance between output sequence and target sequence:
Wherein τ is a constant, takes τ=10, and f (t) and g (t) are respectively two filter functions of pulse train.Selection is most
Classification corresponding to small Dis is used as the last result classified.
Compared with prior art, the present invention has the following advantages:
The present invention is inspired by biological vision hierarchical system, in the characteristic extraction part of image, is processed using human eye and connect
The form of image is received, using the cell operating mechanism of HMAX modeling receptive fields, first with the side of Gabor filtering reinforcing images
Edge information, then maximum pond treatment is carried out to the image by the filtered all directions of Gabor, reach the topmost feature of extraction
And the purpose of dimension-reduction treatment.This causes that the present invention has certain biological basis.In character image data processing method, select
Phase coding technology, by the Pixel Information of image is converted to pulse phenomenon, so not only allows for the spatial information of image, also
Consider the temporal information of image.In learning algorithm, impulsive neural networks (SNN) are selected, this is third generation neutral net,
The biological nerve information transmission means of vivider simulation, has been greatly reduced the power consumption of experiment.
The present invention proposes a kind of image-recognizing method based on biological vision and precision pulse driving neutral net.Experiment
Prove, the present invention have certain biological basis, with good feasibility and robustness, and its for image identification with
Classification, especially the accuracy in noise image is greatly improved.
Brief description of the drawings
Fig. 1 is the system of the image-recognizing method that neutral net is driven based on biological vision and precision pulse of the present invention
Structure chart;
Fig. 2 is the graph of a relation that the cell in receptive field interacts;
Fig. 3 is the schematic diagram how PSD rules change synapse weight by output pulse sequence and target pulse sequence;
Fig. 4 is that, using different learning rules, the noise image to having 10% is classified with regard to comparative result figure.
Specific embodiment
The present invention is further described below in conjunction with the accompanying drawings.
In Fig. 1, the system knot based on biological vision with the image-recognizing method of precision pulse driving neutral net is described
Composition, detailed description is given with reference to Fig. 1.
Step S1, feature extraction
1.1 Gabor filtering process
When the V1 areas simple cell of receptive field carries out the matching of unit, extract special using the higher order filter of sparse coding
Levy, and the computation model of sparse coding is established using two-dimensional Gabor filter function.The general type of sparse coding is:
SC=AH
Wherein sci, ai, hjIt is sparse piece of element of SC of unit, A is the basic function of sparse coding, and H is sparse.A's
The most frequently used expression-form is:
||·||fIt is Frobenius normal forms, μ is normal number.But sparse coding typically uses Independent Component Analysis
Image is processed, this causes that it is to need very big memory headroom to calculate view data, is unfavorable for practical operation.And Gabor
Memory headroom needed for filtering is small, and Gabor responds the form for being converted into sparse coding that G (x, y) can be approximate:
G (x, y)=S (x, y) K (x, y),
Wherein S (x, y) represents complicated sine functions, and its span is [- 1,1], therefore she meets above-mentioned base letter
The form of number A.K (x, y) is the envelope function of two-dimensional discrete Gauss equation, and λ represents wavelength, and its value is no more than image length and width
1/5.It is phase offset, at [- 180 °, 180 °], γ represents length-width ratio to value, it determines that image is filtered by Gabor
Shape afterwards.σ depends on bandwidth b:
For simplicity the real part part filtered using Gabor is learnt to characteristics of image:
X'=x cos θ+y sin θs, y'=-x sin θ+y cos θ
Offset phase is set respectivelyWavelength X and bandwidth b are 0 °, 10 and 1, therefore σ=0.56 λ.
In Gabor filtering, the Gabor filtering of (0 °, 45 °, 90 °, 135 °) four direction is chosen, and by its result normalizing
Change to [- 1,1].
1.2 maximum pond treatment
Image enhances its marginal information after being filtered through Gabor, and extraction and the dimensionality reduction of feature are carried out using maximum pond, its
Embody as follows:
Wherein m is the size of the sliding window of maximum pond operation.In former HMAX models, maximum pond operation is to warp
Filtered 4 directions of Gabor take overall maximum, and consider that human eye is different to the susceptibility of all directions in the present invention
And its pertinent literature, 4 pictures in direction have all been carried out with maximum pond operation.
Step S2, phase code
Selected phase encryption algorithm (a kind of time encoding scheme) produces pulse train.The intensity of each pixel in RF
Value is converted into a rectilinear oscillation for the time action potential for processing meticulously, and this is described as cosine function:
WhereinIt is i-th concussion function of encoding nerve unit, in periodically;A is amplitude, and ω represents angular speed, φ0
It is initial phase, i-th offset phase φ of encoding nerve unitiComputing formula be:
φi=φ0+(i-1)·Δφ
Wherein Δ φ is minimum offset identity, and its value is 2 π/n, and n is the number of neuron.Concussion cycle t is setmaxFor
200ms.Each pixel of image is represented with for example following formula of the relation of time:
Wherein xiThe pixel value of representative image ith pixel.When the incoming coding layer of pixel, will cause upwardly or downwardly
Film vibration, if film potential exceed threshold value, stimulate produce.The product of pulse train can be controlled by adjusting amplitude and threshold value
It is raw.
Step S3, pulse study
Impulsive neural networks mainly learn to the pulse train that image is produced, and pulse train is represented by:
Wherein, tfF-th pulse Time Of Release is represented, δ (x) represents Dirac delta functions, at that time x=0, δ (x)=
1, otherwise δ (x)=0.
PSD rules are learnt using precise time pulse coded information to the pulse train of image, and its basis is leaky
Integrate-and-fire models.When weight is adjusted using this learning rules, postsynaptic potential (PSP) is all inputs
The summation of the weight of the afferent nerve of pulse:
Wherein ωiAnd tiIt is respectively synapse weight and the duration of ignition of i & lt input, VrestIt is reset voltage.K is double fingers
The kernel function of number form formula:
Wherein tfIt is i-th f-th pulse of neuron generation;V0It is normalized parameter, it makes the value of K be not more than 1;
τsExpression slow-decay constant, and τfRefer to rapid decay constant, make τs/τf=4.Postsynaptic currents be PSD rule in one it is important
Parameter, it meets following formula:
WhereinIt is the synaptic currents of i & lt input;H (x) is Heaviside functions, works as x<Its value is 0 when 0, works as x=
Its value is 0.5 when 0, works as x>Its value is 1 when 0.Widrow-Hoff rule synapse weight Changing Pattern be:
And weight change can be typically expressed as:
PSD rules change the inspiration that synapse weight receives Widrow-Hoff rules, and its form is:
In the study stage, the step-length of impulsive neural networks is set to 100 times.
Step S4, discriminant classification
Image sequence by after PSD rule learnings, set of pulses output sequence can be produced, using van Rossum
Metric carries out discriminant classification to result.This method depends on the distance between output sequence and target sequence:
Wherein τ is a constant, takes τ=10, and f (t) and g (t) are respectively two filter functions of pulse train.Selection is most
Classification corresponding to small Dis is used as the last result classified.
The structure of biological vision hierarchical system is as shown in Fig. 2 the cell in receptive field can be divided into two kinds:Simple cell
(simple cell) and complex cell (complex cell).Simple cell carries out sparse coding operation, and complex cell is carried out most
Great Chi is operated.HMAX is an object identification model for really being able to imitative visual structure work, and it is based on being confirmed on biology
Gabor wavelet base and multilayer feature combination, and using the filter response on adjacent space and yardstick take maximum and extract, make
Obtain image table and reveal the features such as yardstick and translation invariant, and a vector will be converted to per pictures.
Describe how PSD rules change synapse weight by output pulse sequence and target pulse sequence in figure 3.
For the multiple input pulse sequence S for givingi(t) and multiple target pulse sequence SdT (), finds impulsive neural networks suitable
Synaptic weight matrix w, makes the output pulse sequence S of neurono(t) and corresponding target pulse sequence Sd(t) as close possible to,
I.e. both error assessment functional values are minimum.
Fig. 4 is the displaying of experimental result, the image recognition of vision layered system combination PSD rule proposed by the present invention and point
Class algorithm, with good robustness.Its concrete operations is as follows:
For a big small picture for n × n, it is expressed as:
Input direction [0 °, 45 °, 90 °, 135 °] will be distinguished after its binaryzation, window size is mG×mGGabor filtering
In, obtain the filtering image that four width sizes are n × n:
It is m that this four width image is distinguished into incoming window sizep×mpMaximum pond in, and the image that will be obtained once splices,
Then new images are converted into a vector:
This vector is input in phase code and obtains pulse trainIt is entered into PSD algorithms, utilizes
The rule of supervised learning, obtains synapse weight matrix:
Wherein c is the classification sum of classification.
When classifying to test set image, by input pulse sequenceIn coming into PSD neutral nets, with cynapse
Weight matrix carries out being calculated a group output pulse sequence accordinglyRespectively by itself and expectation pulse train Sd
T () calculates Dis, according to classifying rules to final result.As can be drawn from Figure 4, the present invention better than general image recognition and
Sorting algorithm, there is good robustness and accuracy of identification.
Claims (1)
1. a kind of image-recognizing method for driving neutral net based on biological vision and precision pulse, it is characterised in that the method bag
Include following steps:
The feature extraction of step 1. biological vision system
Step 1.1.S1 layers of Gabor filtering process
S1 layers of representative is mode that simple cell in visual cortex receptive field processes picture signal;The V1 areas of receptive field are simple
When cell carries out the matching of unit, feature is extracted using the higher order filter of sparse coding;The form of sparse coding is:
SC=AH
Wherein sci, ai, hjIt is sparse piece of element of SC of unit, A is the basic function of sparse coding, and H is sparse;The expression of A
Form is:
||·||fIt is Frobenius normal forms, μ is normal number;What Gabor responded that G (x, y) can be approximate is converted into sparse coding
Form:
G (x, y)=S (x, y) K (x, y),
Wherein S (x, y) represents complicated sine functions, and its span is [- 1,1], therefore meets the shape of above-mentioned basic function A
Formula;K (x, y) is the envelope function of two-dimensional discrete Gauss equation, and λ represents wavelength, 1/5 of its value no more than image length and width;
It is phase offset, at [- 180 °, 180 °], γ represents length-width ratio to value, and it determines image by the filtered shapes of Gabor;
σ depends on bandwidth b:
The real part part filtered using Gabor is learnt to characteristics of image:
X'=x cos θ+y sin θs, y'=-x sin θ+y cos θ
And offset phase is set respectivelyWavelength X and bandwidth b are 0 °, 10 and 1, therefore σ=0.56 λ;
In S1 layers, small greatly to one is the picture of n × n, 0 ° of selection, 45 °, 90 °, 135 ° of four directions, and window size is mG×
mGGabor filtering, obtain the filtering image that four width sizes are n × n:
The max pooling treatment of C1 layers of step 1.2.
Image enhances its marginal information after S1 layers, carries out extraction and the dimensionality reduction of feature using max pooling at C1 layers,
It embodies as follows:
Wherein m is the size of the sliding window of max pooling;The image that will be obtained once splices, and then changes new images
It is a vector:
Step 2. pulse code
Selected phase encodes to produce pulse train;The structure of coding unit is made up of three parts:Positive neuron, negative neuronal
Unit, output neuron;In whole cataloged procedure, each incoming spiking represents a neuron activity, is connected to
One receptive field region, i.e., one coding unit is connected to a pixel;Subthreshold membrane potential oscillation is also related to action potential,
The intensity level of each pixel is converted into a rectilinear oscillation for the time action potential for processing meticulously in RF, is described as cosine letter
Number:
WhereinIt is i-th concussion function of encoding nerve unit, in periodically;A is amplitude, and ω represents angular speed, φ0It is just
Beginning phase, i-th offset phase φ of encoding nerve unitiComputing formula be:
φi=φ0+(i-1)·Δφ
Wherein Δ φ is minimum offset identity, and its value is 2 π/n, and n is the number of neuron;Concussion cycle t is setmaxFor
200ms;Each pixel of image is represented with for example following formula of the relation of time:
Wherein xiThe pixel value of representative image ith pixel;When the incoming coding layer of pixel, film upwardly or downwardly will be caused
Vibration, if film potential exceedes threshold value, stimulates and produces;The generation of pulse train can be controlled by adjusting amplitude and threshold value;
Step 3. impulsive neural networks learn
Impulsive neural networks mainly learn to the pulse train that image is produced, and pulse train is expressed as:
Wherein, tfF-th pulse Time Of Release is represented, δ (x) represents Dirac delta functions, at that time x=0, δ (x)=1, otherwise
δ (x)=0;
PSD rules are learnt using precise time pulse coded information to the pulse train of image, and its basis is leaky
Integrate-and-fire models;When weight is adjusted using this learning rules, postsynaptic potential is all input pulses
Afferent nerve weight summation:
Wherein ωiAnd tiIt is respectively synapse weight and the duration of ignition of i & lt input, VrestIt is reset voltage;K is double index shapes
The kernel function of formula:
Wherein tfIt is i-th f-th pulse of neuron generation;V0It is normalized parameter, it makes the value of K be not more than 1;τsTable
Show slow-decay constant, and τfRefer to rapid decay constant, make τs/τf=4;Postsynaptic currents are an important ginsengs in PSD rules
Number, it meets following formula:
WhereinIt is the synaptic currents of i & lt input;H (x) is Heaviside functions, works as x<Its value is 0 when 0, as x=0
Its value is 0.5, works as x>Its value is 1 when 0;Widrow-Hoff rule synapse weight Changing Pattern be:
And weight change is represented by:
PSD rules change the inspiration that synapse weight receives Widrow-Hoff rules, and its form is:
In the study stage, the step-length of impulsive neural networks is set to 100 times;The above-mentioned pulse train that obtains is input to PSD rules
In, using the rule of supervised learning, obtain synapse weight matrix:
Wherein c is the classification sum of classification;
Step 4. discriminant classification
Image sequence by after PSD rule learnings, set of pulses output sequence can be produced, using van Rossum metric couple
Result carries out discriminant classification;It depends on the distance between output sequence and target sequence:
Wherein τ is a constant, and f (t) and g (t) are respectively two filter functions of pulse train;Select minimum Dis institutes right
The classification answered is used as the last result classified.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710036419.6A CN106845541A (en) | 2017-01-17 | 2017-01-17 | A kind of image-recognizing method based on biological vision and precision pulse driving neutral net |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710036419.6A CN106845541A (en) | 2017-01-17 | 2017-01-17 | A kind of image-recognizing method based on biological vision and precision pulse driving neutral net |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106845541A true CN106845541A (en) | 2017-06-13 |
Family
ID=59124308
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710036419.6A Pending CN106845541A (en) | 2017-01-17 | 2017-01-17 | A kind of image-recognizing method based on biological vision and precision pulse driving neutral net |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106845541A (en) |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107403154A (en) * | 2017-07-20 | 2017-11-28 | 四川大学 | A kind of gait recognition method based on dynamic visual sensor |
CN108010046A (en) * | 2017-12-14 | 2018-05-08 | 广西科技大学 | Based on the bionical profile testing method for improving classical receptive field |
CN108197711A (en) * | 2017-12-13 | 2018-06-22 | 中国科学院自动化研究所 | The computational methods for paying attention to switching are felt based on class brain more |
CN108416391A (en) * | 2018-03-16 | 2018-08-17 | 重庆大学 | The image classification method of view-based access control model cortex treatment mechanism and pulse supervised learning |
CN108446757A (en) * | 2017-12-29 | 2018-08-24 | 北京理工大学 | A kind of cascade speed identifying system of multistage delay and method based on impulsive neural networks |
CN108710770A (en) * | 2018-05-31 | 2018-10-26 | 杭州电子科技大学 | A kind of accurate cynapse method of adjustment towards the study of multiple-pulse Neural Network Supervised |
CN108985447A (en) * | 2018-06-15 | 2018-12-11 | 华中科技大学 | A kind of hardware pulse nerve network system |
CN109102000A (en) * | 2018-09-05 | 2018-12-28 | 杭州电子科技大学 | A kind of image-recognizing method extracted based on layered characteristic with multilayer impulsive neural networks |
CN109522448A (en) * | 2018-10-18 | 2019-03-26 | 天津大学 | A method of robustness speech Gender Classification is carried out based on CRBM and SNN |
CN109616104A (en) * | 2019-01-31 | 2019-04-12 | 天津大学 | Ambient sound recognition methods based on key point coding and multiple-pulse study |
CN109803096A (en) * | 2019-01-11 | 2019-05-24 | 北京大学 | A kind of display methods and system based on pulse signal |
CN110223263A (en) * | 2019-04-23 | 2019-09-10 | 上海上湖信息技术有限公司 | Imaging direction detection method and device, readable storage medium storing program for executing |
CN110427823A (en) * | 2019-06-28 | 2019-11-08 | 北京大学 | Joint objective detection method and device based on video frame and pulse array signals |
CN110555523A (en) * | 2019-07-23 | 2019-12-10 | 中建三局智能技术有限公司 | short-range tracking method and system based on impulse neural network |
CN110826749A (en) * | 2018-08-07 | 2020-02-21 | 中国农业大学 | Dissolved oxygen content prediction method based on SNN, electronic device and system |
CN111046954A (en) * | 2019-12-12 | 2020-04-21 | 电子科技大学 | Image classification method of spiking learning model based on dynamic threshold |
CN111488908A (en) * | 2020-03-10 | 2020-08-04 | 天津大学 | Brain-imitating image identification method based on enhanced pulse |
CN111797968A (en) * | 2020-06-19 | 2020-10-20 | 武汉大学 | Reweighting sparse reconstruction method based on impulse neural network |
CN112580737A (en) * | 2020-12-25 | 2021-03-30 | 航天科工网络信息发展有限公司 | Pulse neural network feature extraction method based on multi-scale feature fusion |
CN112597980A (en) * | 2021-03-04 | 2021-04-02 | 之江实验室 | Brain-like gesture sequence recognition method for dynamic vision sensor |
US11228758B2 (en) | 2016-01-22 | 2022-01-18 | Peking University | Imaging method and device |
CN114202068A (en) * | 2022-02-17 | 2022-03-18 | 浙江大学 | Self-learning implementation system for brain-like computing chip |
CN116541680A (en) * | 2023-07-06 | 2023-08-04 | 北京航空航天大学 | Industrial equipment state prediction method and device based on light-weight time sequence reduction |
CN116989800A (en) * | 2023-09-27 | 2023-11-03 | 安徽大学 | Mobile robot visual navigation decision-making method based on pulse reinforcement learning |
CN117152637A (en) * | 2023-10-30 | 2023-12-01 | 中国海洋大学 | Strong convection cloud identification method based on FY-4A satellite cloud image prediction sequence |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105404902A (en) * | 2015-10-27 | 2016-03-16 | 清华大学 | Impulsive neural network-based image feature describing and memorizing method |
CN105760930A (en) * | 2016-02-18 | 2016-07-13 | 天津大学 | Multilayer spiking neural network recognition system for AER |
-
2017
- 2017-01-17 CN CN201710036419.6A patent/CN106845541A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105404902A (en) * | 2015-10-27 | 2016-03-16 | 清华大学 | Impulsive neural network-based image feature describing and memorizing method |
CN105760930A (en) * | 2016-02-18 | 2016-07-13 | 天津大学 | Multilayer spiking neural network recognition system for AER |
Non-Patent Citations (2)
Title |
---|
XIAOLIANG XU ET AL.: "A Hierarchical Visual Recognition Model with Precise-Spike-Driven Synaptic Plasticity", 《COMPUTATIONAL INTELLIGENCE IEEE,2016》 * |
张玉平: "递归脉冲神经网络的监督学习及图形识别研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11800098B2 (en) | 2016-01-22 | 2023-10-24 | Spike Vision (Beijing) Technology Co., Ltd. | Imaging method and device |
US11228758B2 (en) | 2016-01-22 | 2022-01-18 | Peking University | Imaging method and device |
CN107403154A (en) * | 2017-07-20 | 2017-11-28 | 四川大学 | A kind of gait recognition method based on dynamic visual sensor |
CN108197711A (en) * | 2017-12-13 | 2018-06-22 | 中国科学院自动化研究所 | The computational methods for paying attention to switching are felt based on class brain more |
CN108197711B (en) * | 2017-12-13 | 2020-02-28 | 中国科学院自动化研究所 | Computing method based on brain-like multi-sensation attention switching |
CN108010046A (en) * | 2017-12-14 | 2018-05-08 | 广西科技大学 | Based on the bionical profile testing method for improving classical receptive field |
CN108446757A (en) * | 2017-12-29 | 2018-08-24 | 北京理工大学 | A kind of cascade speed identifying system of multistage delay and method based on impulsive neural networks |
CN108446757B (en) * | 2017-12-29 | 2020-09-01 | 北京理工大学 | Multi-stage delay cascade speed identification system and method based on impulse neural network |
CN108416391A (en) * | 2018-03-16 | 2018-08-17 | 重庆大学 | The image classification method of view-based access control model cortex treatment mechanism and pulse supervised learning |
CN108416391B (en) * | 2018-03-16 | 2020-04-24 | 重庆大学 | Image classification method based on visual cortex processing mechanism and pulse supervised learning |
CN108710770A (en) * | 2018-05-31 | 2018-10-26 | 杭州电子科技大学 | A kind of accurate cynapse method of adjustment towards the study of multiple-pulse Neural Network Supervised |
CN108985447A (en) * | 2018-06-15 | 2018-12-11 | 华中科技大学 | A kind of hardware pulse nerve network system |
CN110826749A (en) * | 2018-08-07 | 2020-02-21 | 中国农业大学 | Dissolved oxygen content prediction method based on SNN, electronic device and system |
CN109102000B (en) * | 2018-09-05 | 2021-09-07 | 杭州电子科技大学 | Image identification method based on hierarchical feature extraction and multilayer pulse neural network |
CN109102000A (en) * | 2018-09-05 | 2018-12-28 | 杭州电子科技大学 | A kind of image-recognizing method extracted based on layered characteristic with multilayer impulsive neural networks |
CN109522448A (en) * | 2018-10-18 | 2019-03-26 | 天津大学 | A method of robustness speech Gender Classification is carried out based on CRBM and SNN |
CN109522448B (en) * | 2018-10-18 | 2021-07-13 | 天津大学 | Method for carrying out robust speech gender classification based on CRBM and SNN |
CN109803096A (en) * | 2019-01-11 | 2019-05-24 | 北京大学 | A kind of display methods and system based on pulse signal |
US10937132B2 (en) | 2019-01-11 | 2021-03-02 | Peking University | Spike signal-based display method and system |
CN109803096B (en) * | 2019-01-11 | 2020-08-25 | 北京大学 | Display method and system based on pulse signals |
CN109616104A (en) * | 2019-01-31 | 2019-04-12 | 天津大学 | Ambient sound recognition methods based on key point coding and multiple-pulse study |
CN109616104B (en) * | 2019-01-31 | 2022-12-30 | 天津大学 | Environment sound identification method based on key point coding and multi-pulse learning |
CN110223263B (en) * | 2019-04-23 | 2021-07-13 | 上海上湖信息技术有限公司 | Imaging direction detection method and device and readable storage medium |
CN110223263A (en) * | 2019-04-23 | 2019-09-10 | 上海上湖信息技术有限公司 | Imaging direction detection method and device, readable storage medium storing program for executing |
CN110427823A (en) * | 2019-06-28 | 2019-11-08 | 北京大学 | Joint objective detection method and device based on video frame and pulse array signals |
CN110555523B (en) * | 2019-07-23 | 2022-03-29 | 中建三局智能技术有限公司 | Short-range tracking method and system based on impulse neural network |
CN110555523A (en) * | 2019-07-23 | 2019-12-10 | 中建三局智能技术有限公司 | short-range tracking method and system based on impulse neural network |
WO2021012752A1 (en) * | 2019-07-23 | 2021-01-28 | 中建三局智能技术有限公司 | Spiking neural network-based short-range tracking method and system |
CN111046954A (en) * | 2019-12-12 | 2020-04-21 | 电子科技大学 | Image classification method of spiking learning model based on dynamic threshold |
CN111488908A (en) * | 2020-03-10 | 2020-08-04 | 天津大学 | Brain-imitating image identification method based on enhanced pulse |
CN111797968A (en) * | 2020-06-19 | 2020-10-20 | 武汉大学 | Reweighting sparse reconstruction method based on impulse neural network |
CN112580737A (en) * | 2020-12-25 | 2021-03-30 | 航天科工网络信息发展有限公司 | Pulse neural network feature extraction method based on multi-scale feature fusion |
CN112597980A (en) * | 2021-03-04 | 2021-04-02 | 之江实验室 | Brain-like gesture sequence recognition method for dynamic vision sensor |
CN114202068A (en) * | 2022-02-17 | 2022-03-18 | 浙江大学 | Self-learning implementation system for brain-like computing chip |
CN114202068B (en) * | 2022-02-17 | 2022-06-28 | 浙江大学 | Self-learning implementation system for brain-like computing chip |
CN116541680B (en) * | 2023-07-06 | 2023-09-12 | 北京航空航天大学 | Industrial equipment state prediction method and device based on light-weight time sequence reduction |
CN116541680A (en) * | 2023-07-06 | 2023-08-04 | 北京航空航天大学 | Industrial equipment state prediction method and device based on light-weight time sequence reduction |
CN116989800A (en) * | 2023-09-27 | 2023-11-03 | 安徽大学 | Mobile robot visual navigation decision-making method based on pulse reinforcement learning |
CN117152637A (en) * | 2023-10-30 | 2023-12-01 | 中国海洋大学 | Strong convection cloud identification method based on FY-4A satellite cloud image prediction sequence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106845541A (en) | A kind of image-recognizing method based on biological vision and precision pulse driving neutral net | |
CN107273845B (en) | Facial expression recognition method based on confidence region and multi-feature weighted fusion | |
CN104537393B (en) | A kind of traffic sign recognition method based on multiresolution convolutional neural networks | |
CN103996056B (en) | Tattoo image classification method based on deep learning | |
US11531876B2 (en) | Deep learning for characterizing unseen categories | |
CN107657204A (en) | The construction method and facial expression recognizing method and system of deep layer network model | |
Boughrara et al. | MLP neural network based face recognition system using constructive training algorithm | |
Tavanaei et al. | Acquisition of visual features through probabilistic spike-timing-dependent plasticity | |
CN105760930A (en) | Multilayer spiking neural network recognition system for AER | |
CN105095833A (en) | Network constructing method for human face identification, identification method and system | |
CN109102000A (en) | A kind of image-recognizing method extracted based on layered characteristic with multilayer impulsive neural networks | |
KR20200121206A (en) | Teacher-student framework for light weighted ensemble classifier combined with deep network and random forest and the classification method based on thereof | |
CN106485259A (en) | A kind of image classification method based on high constraint high dispersive principal component analysiss network | |
CN106980830A (en) | One kind is based on depth convolutional network from affiliation recognition methods and device | |
Peemen et al. | Efficiency optimization of trainable feature extractors for a consumer platform | |
CN105894018A (en) | Polarized SAR image classification method based deep multi-example learning | |
Wan et al. | A novel face recognition method: Using random weight networks and quasi-singular value decomposition | |
Sun et al. | A spiking neural network for extraction of features in colour opponent visual pathways and FPGA implementation | |
CN114241458A (en) | Driver behavior recognition method based on attitude estimation feature fusion | |
Ribeiro et al. | Extreme learning classifier with deep concepts | |
Poggio | The computational magic of the ventral stream | |
Zhang et al. | Image exploration procedure classification with spike-timing neural network for the blind | |
Kumar et al. | Discriminating real from fake smile using convolution neural network | |
Darestani et al. | Face recognition using contourlet-based features and hybrid PSO-neural model | |
Suchy et al. | Fusion of deep convolutional neural networks |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170613 |
|
RJ01 | Rejection of invention patent application after publication |