SlideShare uma empresa Scribd logo
1 de 62
Jason Tsai (蔡志順)
Oct. 19, 2019 @Mozilla Community Space Taipei
*Picture adopted from
https://bit.ly/2ts8xCk
Introduction to Spiking Neural Networks
*Copyright Notice:
All figures in this presentation are taken from
the quoted sources as mentioned in the
respective slides and their copyright belongs
to the owners. This presentation itself adopts
Creative Commons license.
Neural Networks 3D Simulation
(Video demo)
*Video from https://youtu.be/3JQ3hYko51Y
Questions
 What are the advantages of spiking
neural networks and neuromorphic
computing?
 What are current challenges of spiking
neural networks (SNNs)?
Characteristics of SNNs
 Spatio-temporal
 Asynchronous
 Sparsity
 Additive weight operation*
 Energy-efficient
 Stochastic
 Robust to noise
Outlines
• Basic neuroscience
• Learning algorithms
• Neuron models
• Neural encoding schemes
• Neuromorphic platforms
Prerequisite
Neuroscience
Nerve Cell
(Neuron)
*Figure adopted from Eric R. Kandel, et.al. Principles of Neural Science, Fifth Edition.
McGraw-Hill Education. 2013. Page 22.
Synapse
*Figure adopted from https://bit.ly/2ycOmcq
(ROC means receptor-operated channels)
Neuron’s Spike: Action Potential
*Figure adopted from https://en.wikipedia.org/wiki/Action_potential &
The front cover of “Spikes: Exploring the Neural Code (1999)”
EPSP / IPSP
*Figure adopted from https://bit.ly/2OgAx7z
The Effect of Presynaptic Spikes on
Postsynaptic Neuron
*Figure adopted from Wulfram Gerstner & Werner M. Kistler. Spiking Neuron Models:
Single Neurons, Populations, Plasticity. Cambridge University Press. 2002. Page 5.
Hebb’s Learning Postulate
 "When an axon of cell A is near enough to excite a cell B and
repeatedly or persistently takes part in firing it, some growth
process or metabolic change takes place in one or both cells such
that A's efficiency, as one of the cells firing B, is increased.“*
* Refer to Donald O. Hebb, The Organization of Behavior: A Neuropsychological Theory. 1949 & 2002. Page 62.
 Causality
 Repetition
Long-Term Potentiation (LTP) / Long-
Term Depression (LTD)
 LTP is a long-lasting, activity-dependent increase in synaptic
strength that is a leading candidate as a cellular mechanism
contributing to memory formation in mammals in a very
broadly applicable sense.*
* Refer to J. David Sweatt. Mechanisms of Memory, Second Edition. Academic Press. 2010. Page 112.
Synaptic Plasticity
*Figure adopted from Wulfram Gerstner & Werner M. Kistler. Spiking Neuron Models:
Single Neurons, Populations, Plasticity. Cambridge University Press. 2002. Page 353.
Back-propagating Action Potential (bAP)
*Further reading: https://en.wikipedia.org/wiki/Neural_backpropagation
Induction of tLTP requires activation of the presynaptic
input milliseconds before the bAP in the postsynaptic
dendrite.
*Figure adopted from https://doi.org/10.3389/fnsyn.2011.00004
Spike-Timing-Dependent Plasticity
(STDP)
Experiment Evidence of STDP
 From Wikipedia:
“Henry Markram, when he was in Bert Sakmann's lab and published their
work in 1997, used dual patch clamping techniques to repetitively
activate pre-synaptic neurons 10 milliseconds before activating the post-
synaptic target neurons, and found the strength of the synapse
increased. When the activation order was reversed so that the pre-
synaptic neuron was activated 10 milliseconds after its post-synaptic
target neuron, the strength of the pre-to-post synaptic connection
decreased.
Further work, by Guoqiang Bi, Li Zhang, and Huizhong Tao in Mu-Ming
Poo's lab in 1998, continued the mapping of the entire time course
relating pre- and post-synaptic activity and synaptic change, to show that
in their preparation synapses that are activated within 5-20 ms before a
postsynaptic spike are strengthened, and those that are activated within a
similar time window after the spike are weakened.”
*Further reading: https://en.wikipedia.org/wiki/Spike-timing-dependent_plasticity
Cortical Column
*Figure adopted from https://bit.ly/2OZQpKA
Lateral Inhibition
Lateral inhibition is a Central Nervous System process whereby
application of a stimulus to the center of the receptive field excites a
neuron, but a stimulus applied near the edge inhibits it.
*Figure adopted from https://bit.ly/2yaat37
Lateral Inhibition
(Cont’d)
*Figure adopted from http://wei-space.blogspot.tw/2007/11/lateral-inhibition.html
& https://en.wikipedia.org/wiki/Lateral_inhibition
Hierarchical Sparse Distributed
Representations in Visual Cortex
*Figure adopted from https://bit.ly/2Ov5qV2 & https://bit.ly/2xTS1fw
Dopamine: Essential for Reward
Processing in Mammalian Brain
*Figure adopted from http://www.jneurosci.org/content/29/2/444
Dopamine neurons form huge synaptic contacts to target!
Learning Rule
Two Hot Approaches
 Supervised: Stochastic Gradient Descent
based Backpropagation learning rule
(Treat the membrane potentials of spiking neurons as
differentiable signals, where discontinuities at spike
times are considered as noise.*)
Unsupervised: STDP (Spike-Timing-
Dependent Plasticity) based learning rule
*Refer to Jun Haeng Lee, et al., Training Deep Spiking Neural Networks Using Backpropagation.
Frontiers in Neuroscience, 08 November 2016. https://doi.org/10.3389/fnins.2016.00508
*Refer to Yu, Q., Tang, H., Hu, J., Tan, K.C., Neuromorphic Cognitive Systems: A Learning and Memory
Centered Approach. Springer International Publishing. 2017. Page 9.
STDP Learning Rule
STDP Learning Rule (1-to-1)
*Figure adopted from http://dx.doi.org/10.7551/978-0-262-33027-5-ch037
STDP Learning Rule (2-to-1)
N0 is stimulated until N1 fires, then e0 is stopped for 30 ms.
N2 is stimulated by e2 during those 30 ms.
*Figure adopted from http://dx.doi.org/10.7551/978-0-262-33027-5-ch037
STDP Finds Spike Patterns
*Figure adopted from https://doi.org/10.1371/journal.pone.0001377
Triplet STDP
*Figure adopted from https://doi.org/10.1523/JNEUROSCI.1425-06.2006
Triplet STDP with traces
*Figure adopted from https://doi.org/10.1007/s00422-008-0233-1
Reward-modulated STDP
*Figure adopted from https://doi.org/10.1371/journal.pcbi.1000180
Neural Modeling
1st Generation of Neuron Models
(McCulloch–Pitts Neuron Model)
*Figure adopted from http://wwwold.ece.utep.edu/research/webfuzzy/docs/kk-thesis/kk-thesis-html/node12.html
2nd Generation of Neuron Models
*Figure adopted from http://cs231n.github.io/neural-networks-1/
3rd Generation of Neuron Models
(Spiking Neuron Models)
*Figure adopted from http://kzyjc.cnjournals.com/html/2018/5/20180512.htm
Spiking Neuron Models
Miscellaneous models (integrators / resonators):
 Hodgkin-Huxley model
 Izhikevish model
 Leaky Integrate-and-Fire (LIF) model
 Resonate-and-Fire model
 Spike Response model (SRM)
……
*Further reading: https://en.wikipedia.org/wiki/Biological_neuron_model
& http://www.scholarpedia.org/article/Spike-response_model
Hodgkin-Huxley Model
*Figure adopted from Wulfram Gerstner & Werner M. Kistler. Spiking Neuron Models: Single Neurons,
Populations, Plasticity. Cambridge University Press. 2002. Page 34.
Hodgkin-Huxley Model (Cont’d)
*Taken from: https://www.bonaccorso.eu/2017/08/19/hodgkin-huxley-spiking-neuron-model-python/amp/
Izhikevich Model
*Taken from: http://www.physics.usyd.edu.au/teach_res/mp/ns/doc/nsIzhikevich3.htm
Izhikevich Model (Cont’d)
*Refer to Simple Model of Spiking Neurons (2003) https://www.izhikevich.org/publications/spikes.htm
Leaky Integrate-and-Fire Model
*Figure adopted from Wulfram Gerstner, Werner M. Kistler, Richard Naud and Liam Paninski “Neuronal Dynamics:
From Single Neurons to Networks and Models of Cognition” Cambridge University Press. 2014. Page 11.
The Firing of a Leaky Integrate-and-
Fire Model Neuron
*Figure adopted from https://doi.org/10.1371/journal.pone.0001377
Resonate-and-Fire Model
*Refer to Resonate-and-Fire Neurons (2001) https://www.izhikevich.org/publications/resfire.htm
Neural Coding
Hypothesized Neural Coding Schemes
 Rate Coding
 Temporal Coding
 Population Coding
 Sparse Coding
*Further reading: https://en.wikipedia.org/wiki/Neural_coding
Rate Coding
*Further reading: http://lcn.epfl.ch/~gerstner/SPNM/node7.html
Rate as a Spike Density
Rate as a Population Activity
Temporal Coding
*Further reading: http://lcn.epfl.ch/~gerstner/SPNM/node8.html
Time-to-First-Spike
(Latency Code)
Firing at Phases respecting
to Oscillation
Interspike synchrony
Population Coding
*Figure adopted from https://doi.org/10.1038/35039062
Sparse Coding
*Figure adopted from http://brainworkshow.sparsey.com/measuring-similarity-in-localist-vs-distributed-representations/
Sparse Coding with Inhibitory Neurons
 Population sparseness: Few neurons are
active at any given time
 Lifetime sparseness: Individual neurons
are responsive to few specific stimuli
*Figure adopted from https://doi.org/10.1523/JNEUROSCI.4188-12.2013
Neuromorphic
Computing
Categories of AI Chips
 AI Accelerator
 GPU
 FPGA
 ASIC
 Neuromorphic chip
 Network-on-Chip
 Memory-based
 Memristor-based
 Many-core CPU
 DSP
 Spintronics-based
 Photonics-based
Why Neuromorphic
*Figure adopted from https://bit.ly/31v1NAS
IBM’s TrueNorth Chip
*Figure adopted from https://doi.org/10.1126/science.1254642
*Video demo https://youtu.be/7ELRZrjCFd0
Intel’s Loihi Chip
*Figure adopted from https://doi.org/10.1109/MM.2018.112130359
*Video demo https://youtu.be/cDKnt9ldXv0
BrainChip’s Akida NSoC
*Figure adopted from https://www.brainchipinc.com/products/akida-neuromorphic-system-on-chip
*Video demo https://bit.ly/35rea45
北京清華大學「天機芯」
*Video demo https://youtu.be/Nf0qVjT9WV0
*Figure adopted from https://doi.org/10.1038/s41586-019-1424-8
ANN-to-SNN Conversion
 Train ANNs using standard supervised training
techniques like backpropagation to leverage
the superior performance of trained ANNs and
subsequently convert to event-driven SNNs for
inference operation on neuromorphic platform.
 Rate-encoded spikes are approximately
proportional to the magnitude of the original
ANN inputs.
ANN-to-SNN Conversion
(Cont’d)
*Figure adopted from https://arxiv.org/abs/1802.02627
A Poisson event-generation process is used to produce the input spike
train to the network.
Software Simulation
 MATLAB
 PyNN http://neuralensemble.org/PyNN/
 BindsNET (with PyTorch)
https://github.com/Hananel-Hazan/bindsnet
 Brian http://briansimulator.org/
 Nengo https://www.nengo.ai/
 NEST http://www.nest-simulator.org/
Further Reading
 Wulfram Gerstner & Werner M. Kistler, “Spiking Neuron Models:
Single Neurons, Populations, Plasticity”. Cambridge University
Press (2002)
 Wulfram Gerstner, Werner M. Kistler, Richard Naud and Liam
Paninski, “Neuronal Dynamics: From Single Neurons to Networks
and Models of Cognition”. Cambridge University Press (2014)
 Eugene M. Izhikevich, “The Dynamical Systems in Neuroscience:
Geometry of Excitability and Bursting”. The MIT Press (2007)
 Nikola K. Kasabov, “Time-Space, Spiking Neural Networks and
Brain-Inspired Artificial Intelligence”. Springer International
Publishing (2018)
 蔺想红、王向文, “脉冲神经网络原理及应用”. 科学出版社 (2018)

Mais conteúdo relacionado

Mais procurados

Fault detection and_diagnosis
Fault detection and_diagnosisFault detection and_diagnosis
Fault detection and_diagnosisM Reza Rahmati
 
Attention scores and mechanisms
Attention scores and mechanismsAttention scores and mechanisms
Attention scores and mechanismsJaeHo Jang
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learningleopauly
 
Neural network
Neural network Neural network
Neural network Faireen
 
Artificial neural network by arpit_sharma
Artificial neural network by arpit_sharmaArtificial neural network by arpit_sharma
Artificial neural network by arpit_sharmaEr. Arpit Sharma
 
Artificial Neural Networks - ANN
Artificial Neural Networks - ANNArtificial Neural Networks - ANN
Artificial Neural Networks - ANNMohamed Talaat
 
Recurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRUananth
 
brain computer-interfaces PPT
 brain computer-interfaces PPT brain computer-interfaces PPT
brain computer-interfaces PPTVijay Mehta
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networksSi Haem
 
Deep Learning - RNN and CNN
Deep Learning - RNN and CNNDeep Learning - RNN and CNN
Deep Learning - RNN and CNNPradnya Saval
 
Emerging trends in brain stimulation
Emerging trends in brain stimulationEmerging trends in brain stimulation
Emerging trends in brain stimulationSujit Kumar Kar
 
The Emerging World of Neuroprosthetics
The Emerging World of NeuroprostheticsThe Emerging World of Neuroprosthetics
The Emerging World of NeuroprostheticsPratik Jain
 
fNIRS and Brain Computer Interface for Communication
fNIRS and Brain Computer Interface for CommunicationfNIRS and Brain Computer Interface for Communication
fNIRS and Brain Computer Interface for CommunicationInsideScientific
 
Intro To Convolutional Neural Networks
Intro To Convolutional Neural NetworksIntro To Convolutional Neural Networks
Intro To Convolutional Neural NetworksMark Scully
 
Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural NetworksAshray Bhandare
 

Mais procurados (20)

Connectome
ConnectomeConnectome
Connectome
 
Fault detection and_diagnosis
Fault detection and_diagnosisFault detection and_diagnosis
Fault detection and_diagnosis
 
Attention scores and mechanisms
Attention scores and mechanismsAttention scores and mechanisms
Attention scores and mechanisms
 
Emg fundamental
Emg fundamentalEmg fundamental
Emg fundamental
 
Data fusion
Data fusionData fusion
Data fusion
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
Neural network
Neural network Neural network
Neural network
 
Neuromorphic computing
Neuromorphic computingNeuromorphic computing
Neuromorphic computing
 
Artificial neural network by arpit_sharma
Artificial neural network by arpit_sharmaArtificial neural network by arpit_sharma
Artificial neural network by arpit_sharma
 
Artificial Neural Networks - ANN
Artificial Neural Networks - ANNArtificial Neural Networks - ANN
Artificial Neural Networks - ANN
 
Recurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRU
 
brain computer-interfaces PPT
 brain computer-interfaces PPT brain computer-interfaces PPT
brain computer-interfaces PPT
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networks
 
Deep Learning - RNN and CNN
Deep Learning - RNN and CNNDeep Learning - RNN and CNN
Deep Learning - RNN and CNN
 
Emerging trends in brain stimulation
Emerging trends in brain stimulationEmerging trends in brain stimulation
Emerging trends in brain stimulation
 
The Emerging World of Neuroprosthetics
The Emerging World of NeuroprostheticsThe Emerging World of Neuroprosthetics
The Emerging World of Neuroprosthetics
 
fNIRS and Brain Computer Interface for Communication
fNIRS and Brain Computer Interface for CommunicationfNIRS and Brain Computer Interface for Communication
fNIRS and Brain Computer Interface for Communication
 
Intro To Convolutional Neural Networks
Intro To Convolutional Neural NetworksIntro To Convolutional Neural Networks
Intro To Convolutional Neural Networks
 
Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networks
 
BRAIN FINGERPRINTING
BRAIN FINGERPRINTINGBRAIN FINGERPRINTING
BRAIN FINGERPRINTING
 

Semelhante a Introduction to Spiking Neural Networks: From a Computational Neuroscience perspective

파이콘 한국 2020) 파이썬으로 구현하는 신경세포 기반의 인공 뇌 시뮬레이터
파이콘 한국 2020) 파이썬으로 구현하는 신경세포 기반의 인공 뇌 시뮬레이터파이콘 한국 2020) 파이썬으로 구현하는 신경세포 기반의 인공 뇌 시뮬레이터
파이콘 한국 2020) 파이썬으로 구현하는 신경세포 기반의 인공 뇌 시뮬레이터Seonghyun Kim
 
Elective Neural Networks. I. The boolean brain. On a Heuristic Point of V...
Elective Neural Networks.   I. The boolean brain.   On a Heuristic Point of V...Elective Neural Networks.   I. The boolean brain.   On a Heuristic Point of V...
Elective Neural Networks. I. The boolean brain. On a Heuristic Point of V...ABINClaude
 
CARLsim 3: Concepts, Tools, and Applications
CARLsim 3: Concepts, Tools, and ApplicationsCARLsim 3: Concepts, Tools, and Applications
CARLsim 3: Concepts, Tools, and ApplicationsMichael Beyeler
 
Fuzzy Logic Final Report
Fuzzy Logic Final ReportFuzzy Logic Final Report
Fuzzy Logic Final ReportShikhar Agarwal
 
ANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMS
ANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMSANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMS
ANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMSIAEME Publication
 
NEURAL NETWORKS
NEURAL NETWORKSNEURAL NETWORKS
NEURAL NETWORKSESCOM
 
fundamentals-of-neural-networks-laurene-fausett
fundamentals-of-neural-networks-laurene-fausettfundamentals-of-neural-networks-laurene-fausett
fundamentals-of-neural-networks-laurene-fausettZarnigar Altaf
 
Artificial Neural Network and its Applications
Artificial Neural Network and its ApplicationsArtificial Neural Network and its Applications
Artificial Neural Network and its Applicationsshritosh kumar
 
Intro to neural networks and fuzzy systems
Intro to neural networks and fuzzy systemsIntro to neural networks and fuzzy systems
Intro to neural networks and fuzzy systemsAmro56
 
SHORT STORY_CMPE255.pptx
SHORT STORY_CMPE255.pptxSHORT STORY_CMPE255.pptx
SHORT STORY_CMPE255.pptxHarikaSatti1
 
How to film firing neurons inside science
How to film firing neurons   inside scienceHow to film firing neurons   inside science
How to film firing neurons inside scienceCurtis Cripe
 
Functional neurological restoration of amputated peripheral nerve using biohy...
Functional neurological restoration of amputated peripheral nerve using biohy...Functional neurological restoration of amputated peripheral nerve using biohy...
Functional neurological restoration of amputated peripheral nerve using biohy...BkesNar
 
Neural Network Presentation Draft Updated March.pptx
Neural Network Presentation Draft Updated March.pptxNeural Network Presentation Draft Updated March.pptx
Neural Network Presentation Draft Updated March.pptxisaac405396
 
Neural Network Presentation Draft Updated March.pptx
Neural Network Presentation Draft Updated March.pptxNeural Network Presentation Draft Updated March.pptx
Neural Network Presentation Draft Updated March.pptxisaac405396
 

Semelhante a Introduction to Spiking Neural Networks: From a Computational Neuroscience perspective (20)

파이콘 한국 2020) 파이썬으로 구현하는 신경세포 기반의 인공 뇌 시뮬레이터
파이콘 한국 2020) 파이썬으로 구현하는 신경세포 기반의 인공 뇌 시뮬레이터파이콘 한국 2020) 파이썬으로 구현하는 신경세포 기반의 인공 뇌 시뮬레이터
파이콘 한국 2020) 파이썬으로 구현하는 신경세포 기반의 인공 뇌 시뮬레이터
 
Elective Neural Networks. I. The boolean brain. On a Heuristic Point of V...
Elective Neural Networks.   I. The boolean brain.   On a Heuristic Point of V...Elective Neural Networks.   I. The boolean brain.   On a Heuristic Point of V...
Elective Neural Networks. I. The boolean brain. On a Heuristic Point of V...
 
Basics of Neural Networks
Basics of Neural NetworksBasics of Neural Networks
Basics of Neural Networks
 
CARLsim 3: Concepts, Tools, and Applications
CARLsim 3: Concepts, Tools, and ApplicationsCARLsim 3: Concepts, Tools, and Applications
CARLsim 3: Concepts, Tools, and Applications
 
Fuzzy Logic Final Report
Fuzzy Logic Final ReportFuzzy Logic Final Report
Fuzzy Logic Final Report
 
ANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMS
ANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMSANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMS
ANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMS
 
Introduction to Neural Network
Introduction to Neural NetworkIntroduction to Neural Network
Introduction to Neural Network
 
Neural Networks: Introducton
Neural Networks: IntroductonNeural Networks: Introducton
Neural Networks: Introducton
 
NEURAL NETWORKS
NEURAL NETWORKSNEURAL NETWORKS
NEURAL NETWORKS
 
fundamentals-of-neural-networks-laurene-fausett
fundamentals-of-neural-networks-laurene-fausettfundamentals-of-neural-networks-laurene-fausett
fundamentals-of-neural-networks-laurene-fausett
 
PhD Defense
PhD DefensePhD Defense
PhD Defense
 
Artificial Neural Network and its Applications
Artificial Neural Network and its ApplicationsArtificial Neural Network and its Applications
Artificial Neural Network and its Applications
 
Intro to neural networks and fuzzy systems
Intro to neural networks and fuzzy systemsIntro to neural networks and fuzzy systems
Intro to neural networks and fuzzy systems
 
SHORT STORY_CMPE255.pptx
SHORT STORY_CMPE255.pptxSHORT STORY_CMPE255.pptx
SHORT STORY_CMPE255.pptx
 
[IJET V2I2P20] Authors: Dr. Sanjeev S Sannakki, Ms.Anjanabhargavi A Kulkarni
[IJET V2I2P20] Authors: Dr. Sanjeev S Sannakki, Ms.Anjanabhargavi A Kulkarni[IJET V2I2P20] Authors: Dr. Sanjeev S Sannakki, Ms.Anjanabhargavi A Kulkarni
[IJET V2I2P20] Authors: Dr. Sanjeev S Sannakki, Ms.Anjanabhargavi A Kulkarni
 
How to film firing neurons inside science
How to film firing neurons   inside scienceHow to film firing neurons   inside science
How to film firing neurons inside science
 
Bc34333339
Bc34333339Bc34333339
Bc34333339
 
Functional neurological restoration of amputated peripheral nerve using biohy...
Functional neurological restoration of amputated peripheral nerve using biohy...Functional neurological restoration of amputated peripheral nerve using biohy...
Functional neurological restoration of amputated peripheral nerve using biohy...
 
Neural Network Presentation Draft Updated March.pptx
Neural Network Presentation Draft Updated March.pptxNeural Network Presentation Draft Updated March.pptx
Neural Network Presentation Draft Updated March.pptx
 
Neural Network Presentation Draft Updated March.pptx
Neural Network Presentation Draft Updated March.pptxNeural Network Presentation Draft Updated March.pptx
Neural Network Presentation Draft Updated March.pptx
 

Mais de Jason Tsai

基於深度學習的人臉辨識技術簡介
基於深度學習的人臉辨識技術簡介基於深度學習的人臉辨識技術簡介
基於深度學習的人臉辨識技術簡介Jason Tsai
 
Neural Network Design: Chapter 17 Radial Basis Networks
Neural Network Design: Chapter 17 Radial Basis NetworksNeural Network Design: Chapter 17 Radial Basis Networks
Neural Network Design: Chapter 17 Radial Basis NetworksJason Tsai
 
Neural Network Design: Chapter 18 Grossberg Network
Neural Network Design: Chapter 18 Grossberg NetworkNeural Network Design: Chapter 18 Grossberg Network
Neural Network Design: Chapter 18 Grossberg NetworkJason Tsai
 
Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生
Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生
Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生Jason Tsai
 
Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生
Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生
Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生Jason Tsai
 
漫談人工智慧:啟發自大腦科學的深度學習網路
漫談人工智慧:啟發自大腦科學的深度學習網路漫談人工智慧:啟發自大腦科學的深度學習網路
漫談人工智慧:啟發自大腦科學的深度學習網路Jason Tsai
 
Reinforcement Learning: Chapter 15 Neuroscience
Reinforcement Learning: Chapter 15 NeuroscienceReinforcement Learning: Chapter 15 Neuroscience
Reinforcement Learning: Chapter 15 NeuroscienceJason Tsai
 
Deep Learning: Chapter 11 Practical Methodology
Deep Learning: Chapter 11 Practical MethodologyDeep Learning: Chapter 11 Practical Methodology
Deep Learning: Chapter 11 Practical MethodologyJason Tsai
 
Deep Learning: Introduction & Chapter 5 Machine Learning Basics
Deep Learning: Introduction & Chapter 5 Machine Learning BasicsDeep Learning: Introduction & Chapter 5 Machine Learning Basics
Deep Learning: Introduction & Chapter 5 Machine Learning BasicsJason Tsai
 
漫談人工智慧:啟發自大腦科學的深度學習網路
漫談人工智慧:啟發自大腦科學的深度學習網路漫談人工智慧:啟發自大腦科學的深度學習網路
漫談人工智慧:啟發自大腦科學的深度學習網路Jason Tsai
 
漫談人工智慧:啟發自大腦科學的深度學習網路
漫談人工智慧:啟發自大腦科學的深度學習網路漫談人工智慧:啟發自大腦科學的深度學習網路
漫談人工智慧:啟發自大腦科學的深度學習網路Jason Tsai
 

Mais de Jason Tsai (11)

基於深度學習的人臉辨識技術簡介
基於深度學習的人臉辨識技術簡介基於深度學習的人臉辨識技術簡介
基於深度學習的人臉辨識技術簡介
 
Neural Network Design: Chapter 17 Radial Basis Networks
Neural Network Design: Chapter 17 Radial Basis NetworksNeural Network Design: Chapter 17 Radial Basis Networks
Neural Network Design: Chapter 17 Radial Basis Networks
 
Neural Network Design: Chapter 18 Grossberg Network
Neural Network Design: Chapter 18 Grossberg NetworkNeural Network Design: Chapter 18 Grossberg Network
Neural Network Design: Chapter 18 Grossberg Network
 
Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生
Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生
Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生
 
Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生
Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生
Convolutional Neural Networks (CNN) — 卷積神經網路的前世今生
 
漫談人工智慧:啟發自大腦科學的深度學習網路
漫談人工智慧:啟發自大腦科學的深度學習網路漫談人工智慧:啟發自大腦科學的深度學習網路
漫談人工智慧:啟發自大腦科學的深度學習網路
 
Reinforcement Learning: Chapter 15 Neuroscience
Reinforcement Learning: Chapter 15 NeuroscienceReinforcement Learning: Chapter 15 Neuroscience
Reinforcement Learning: Chapter 15 Neuroscience
 
Deep Learning: Chapter 11 Practical Methodology
Deep Learning: Chapter 11 Practical MethodologyDeep Learning: Chapter 11 Practical Methodology
Deep Learning: Chapter 11 Practical Methodology
 
Deep Learning: Introduction & Chapter 5 Machine Learning Basics
Deep Learning: Introduction & Chapter 5 Machine Learning BasicsDeep Learning: Introduction & Chapter 5 Machine Learning Basics
Deep Learning: Introduction & Chapter 5 Machine Learning Basics
 
漫談人工智慧:啟發自大腦科學的深度學習網路
漫談人工智慧:啟發自大腦科學的深度學習網路漫談人工智慧:啟發自大腦科學的深度學習網路
漫談人工智慧:啟發自大腦科學的深度學習網路
 
漫談人工智慧:啟發自大腦科學的深度學習網路
漫談人工智慧:啟發自大腦科學的深度學習網路漫談人工智慧:啟發自大腦科學的深度學習網路
漫談人工智慧:啟發自大腦科學的深度學習網路
 

Último

Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...Rick Flair
 
How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.Curtis Poe
 
Testing tools and AI - ideas what to try with some tool examples
Testing tools and AI - ideas what to try with some tool examplesTesting tools and AI - ideas what to try with some tool examples
Testing tools and AI - ideas what to try with some tool examplesKari Kakkonen
 
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...Scott Andery
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfMounikaPolabathina
 
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxPasskey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxLoriGlavin3
 
Potential of AI (Generative AI) in Business: Learnings and Insights
Potential of AI (Generative AI) in Business: Learnings and InsightsPotential of AI (Generative AI) in Business: Learnings and Insights
Potential of AI (Generative AI) in Business: Learnings and InsightsRavi Sanghani
 
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentEmixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentPim van der Noll
 
Modern Roaming for Notes and Nomad – Cheaper Faster Better Stronger
Modern Roaming for Notes and Nomad – Cheaper Faster Better StrongerModern Roaming for Notes and Nomad – Cheaper Faster Better Stronger
Modern Roaming for Notes and Nomad – Cheaper Faster Better Strongerpanagenda
 
Generative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfGenerative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfIngrid Airi González
 
Decarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityDecarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityIES VE
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteDianaGray10
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsPixlogix Infotech
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxLoriGlavin3
 
Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Farhan Tariq
 
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesHow to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesThousandEyes
 
Scale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL RouterScale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL RouterMydbops
 
Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...
Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...
Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...panagenda
 
Time Series Foundation Models - current state and future directions
Time Series Foundation Models - current state and future directionsTime Series Foundation Models - current state and future directions
Time Series Foundation Models - current state and future directionsNathaniel Shimoni
 
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...Wes McKinney
 

Último (20)

Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...
 
How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.
 
Testing tools and AI - ideas what to try with some tool examples
Testing tools and AI - ideas what to try with some tool examplesTesting tools and AI - ideas what to try with some tool examples
Testing tools and AI - ideas what to try with some tool examples
 
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdf
 
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxPasskey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
 
Potential of AI (Generative AI) in Business: Learnings and Insights
Potential of AI (Generative AI) in Business: Learnings and InsightsPotential of AI (Generative AI) in Business: Learnings and Insights
Potential of AI (Generative AI) in Business: Learnings and Insights
 
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentEmixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
 
Modern Roaming for Notes and Nomad – Cheaper Faster Better Stronger
Modern Roaming for Notes and Nomad – Cheaper Faster Better StrongerModern Roaming for Notes and Nomad – Cheaper Faster Better Stronger
Modern Roaming for Notes and Nomad – Cheaper Faster Better Stronger
 
Generative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfGenerative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdf
 
Decarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityDecarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a reality
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test Suite
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and Cons
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
 
Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...
 
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesHow to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
 
Scale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL RouterScale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL Router
 
Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...
Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...
Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...
 
Time Series Foundation Models - current state and future directions
Time Series Foundation Models - current state and future directionsTime Series Foundation Models - current state and future directions
Time Series Foundation Models - current state and future directions
 
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
The Future Roadmap for the Composable Data Stack - Wes McKinney - Data Counci...
 

Introduction to Spiking Neural Networks: From a Computational Neuroscience perspective

  • 1. Jason Tsai (蔡志順) Oct. 19, 2019 @Mozilla Community Space Taipei *Picture adopted from https://bit.ly/2ts8xCk Introduction to Spiking Neural Networks
  • 2. *Copyright Notice: All figures in this presentation are taken from the quoted sources as mentioned in the respective slides and their copyright belongs to the owners. This presentation itself adopts Creative Commons license.
  • 3. Neural Networks 3D Simulation (Video demo) *Video from https://youtu.be/3JQ3hYko51Y
  • 4. Questions  What are the advantages of spiking neural networks and neuromorphic computing?  What are current challenges of spiking neural networks (SNNs)?
  • 5. Characteristics of SNNs  Spatio-temporal  Asynchronous  Sparsity  Additive weight operation*  Energy-efficient  Stochastic  Robust to noise
  • 6. Outlines • Basic neuroscience • Learning algorithms • Neuron models • Neural encoding schemes • Neuromorphic platforms
  • 8. Nerve Cell (Neuron) *Figure adopted from Eric R. Kandel, et.al. Principles of Neural Science, Fifth Edition. McGraw-Hill Education. 2013. Page 22.
  • 9. Synapse *Figure adopted from https://bit.ly/2ycOmcq (ROC means receptor-operated channels)
  • 10. Neuron’s Spike: Action Potential *Figure adopted from https://en.wikipedia.org/wiki/Action_potential & The front cover of “Spikes: Exploring the Neural Code (1999)”
  • 11. EPSP / IPSP *Figure adopted from https://bit.ly/2OgAx7z
  • 12. The Effect of Presynaptic Spikes on Postsynaptic Neuron *Figure adopted from Wulfram Gerstner & Werner M. Kistler. Spiking Neuron Models: Single Neurons, Populations, Plasticity. Cambridge University Press. 2002. Page 5.
  • 13. Hebb’s Learning Postulate  "When an axon of cell A is near enough to excite a cell B and repeatedly or persistently takes part in firing it, some growth process or metabolic change takes place in one or both cells such that A's efficiency, as one of the cells firing B, is increased.“* * Refer to Donald O. Hebb, The Organization of Behavior: A Neuropsychological Theory. 1949 & 2002. Page 62.  Causality  Repetition
  • 14. Long-Term Potentiation (LTP) / Long- Term Depression (LTD)  LTP is a long-lasting, activity-dependent increase in synaptic strength that is a leading candidate as a cellular mechanism contributing to memory formation in mammals in a very broadly applicable sense.* * Refer to J. David Sweatt. Mechanisms of Memory, Second Edition. Academic Press. 2010. Page 112.
  • 15. Synaptic Plasticity *Figure adopted from Wulfram Gerstner & Werner M. Kistler. Spiking Neuron Models: Single Neurons, Populations, Plasticity. Cambridge University Press. 2002. Page 353.
  • 16. Back-propagating Action Potential (bAP) *Further reading: https://en.wikipedia.org/wiki/Neural_backpropagation Induction of tLTP requires activation of the presynaptic input milliseconds before the bAP in the postsynaptic dendrite.
  • 17. *Figure adopted from https://doi.org/10.3389/fnsyn.2011.00004 Spike-Timing-Dependent Plasticity (STDP)
  • 18. Experiment Evidence of STDP  From Wikipedia: “Henry Markram, when he was in Bert Sakmann's lab and published their work in 1997, used dual patch clamping techniques to repetitively activate pre-synaptic neurons 10 milliseconds before activating the post- synaptic target neurons, and found the strength of the synapse increased. When the activation order was reversed so that the pre- synaptic neuron was activated 10 milliseconds after its post-synaptic target neuron, the strength of the pre-to-post synaptic connection decreased. Further work, by Guoqiang Bi, Li Zhang, and Huizhong Tao in Mu-Ming Poo's lab in 1998, continued the mapping of the entire time course relating pre- and post-synaptic activity and synaptic change, to show that in their preparation synapses that are activated within 5-20 ms before a postsynaptic spike are strengthened, and those that are activated within a similar time window after the spike are weakened.” *Further reading: https://en.wikipedia.org/wiki/Spike-timing-dependent_plasticity
  • 19. Cortical Column *Figure adopted from https://bit.ly/2OZQpKA
  • 20. Lateral Inhibition Lateral inhibition is a Central Nervous System process whereby application of a stimulus to the center of the receptive field excites a neuron, but a stimulus applied near the edge inhibits it. *Figure adopted from https://bit.ly/2yaat37
  • 21. Lateral Inhibition (Cont’d) *Figure adopted from http://wei-space.blogspot.tw/2007/11/lateral-inhibition.html & https://en.wikipedia.org/wiki/Lateral_inhibition
  • 22. Hierarchical Sparse Distributed Representations in Visual Cortex *Figure adopted from https://bit.ly/2Ov5qV2 & https://bit.ly/2xTS1fw
  • 23. Dopamine: Essential for Reward Processing in Mammalian Brain *Figure adopted from http://www.jneurosci.org/content/29/2/444 Dopamine neurons form huge synaptic contacts to target!
  • 25. Two Hot Approaches  Supervised: Stochastic Gradient Descent based Backpropagation learning rule (Treat the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are considered as noise.*) Unsupervised: STDP (Spike-Timing- Dependent Plasticity) based learning rule *Refer to Jun Haeng Lee, et al., Training Deep Spiking Neural Networks Using Backpropagation. Frontiers in Neuroscience, 08 November 2016. https://doi.org/10.3389/fnins.2016.00508
  • 26. *Refer to Yu, Q., Tang, H., Hu, J., Tan, K.C., Neuromorphic Cognitive Systems: A Learning and Memory Centered Approach. Springer International Publishing. 2017. Page 9. STDP Learning Rule
  • 27. STDP Learning Rule (1-to-1) *Figure adopted from http://dx.doi.org/10.7551/978-0-262-33027-5-ch037
  • 28. STDP Learning Rule (2-to-1) N0 is stimulated until N1 fires, then e0 is stopped for 30 ms. N2 is stimulated by e2 during those 30 ms. *Figure adopted from http://dx.doi.org/10.7551/978-0-262-33027-5-ch037
  • 29. STDP Finds Spike Patterns *Figure adopted from https://doi.org/10.1371/journal.pone.0001377
  • 30. Triplet STDP *Figure adopted from https://doi.org/10.1523/JNEUROSCI.1425-06.2006
  • 31. Triplet STDP with traces *Figure adopted from https://doi.org/10.1007/s00422-008-0233-1
  • 32. Reward-modulated STDP *Figure adopted from https://doi.org/10.1371/journal.pcbi.1000180
  • 34. 1st Generation of Neuron Models (McCulloch–Pitts Neuron Model) *Figure adopted from http://wwwold.ece.utep.edu/research/webfuzzy/docs/kk-thesis/kk-thesis-html/node12.html
  • 35. 2nd Generation of Neuron Models *Figure adopted from http://cs231n.github.io/neural-networks-1/
  • 36. 3rd Generation of Neuron Models (Spiking Neuron Models) *Figure adopted from http://kzyjc.cnjournals.com/html/2018/5/20180512.htm
  • 37. Spiking Neuron Models Miscellaneous models (integrators / resonators):  Hodgkin-Huxley model  Izhikevish model  Leaky Integrate-and-Fire (LIF) model  Resonate-and-Fire model  Spike Response model (SRM) …… *Further reading: https://en.wikipedia.org/wiki/Biological_neuron_model & http://www.scholarpedia.org/article/Spike-response_model
  • 38. Hodgkin-Huxley Model *Figure adopted from Wulfram Gerstner & Werner M. Kistler. Spiking Neuron Models: Single Neurons, Populations, Plasticity. Cambridge University Press. 2002. Page 34.
  • 39. Hodgkin-Huxley Model (Cont’d) *Taken from: https://www.bonaccorso.eu/2017/08/19/hodgkin-huxley-spiking-neuron-model-python/amp/
  • 40. Izhikevich Model *Taken from: http://www.physics.usyd.edu.au/teach_res/mp/ns/doc/nsIzhikevich3.htm
  • 41. Izhikevich Model (Cont’d) *Refer to Simple Model of Spiking Neurons (2003) https://www.izhikevich.org/publications/spikes.htm
  • 42. Leaky Integrate-and-Fire Model *Figure adopted from Wulfram Gerstner, Werner M. Kistler, Richard Naud and Liam Paninski “Neuronal Dynamics: From Single Neurons to Networks and Models of Cognition” Cambridge University Press. 2014. Page 11.
  • 43. The Firing of a Leaky Integrate-and- Fire Model Neuron *Figure adopted from https://doi.org/10.1371/journal.pone.0001377
  • 44. Resonate-and-Fire Model *Refer to Resonate-and-Fire Neurons (2001) https://www.izhikevich.org/publications/resfire.htm
  • 46. Hypothesized Neural Coding Schemes  Rate Coding  Temporal Coding  Population Coding  Sparse Coding *Further reading: https://en.wikipedia.org/wiki/Neural_coding
  • 47. Rate Coding *Further reading: http://lcn.epfl.ch/~gerstner/SPNM/node7.html Rate as a Spike Density Rate as a Population Activity
  • 48. Temporal Coding *Further reading: http://lcn.epfl.ch/~gerstner/SPNM/node8.html Time-to-First-Spike (Latency Code) Firing at Phases respecting to Oscillation Interspike synchrony
  • 49. Population Coding *Figure adopted from https://doi.org/10.1038/35039062
  • 50. Sparse Coding *Figure adopted from http://brainworkshow.sparsey.com/measuring-similarity-in-localist-vs-distributed-representations/
  • 51. Sparse Coding with Inhibitory Neurons  Population sparseness: Few neurons are active at any given time  Lifetime sparseness: Individual neurons are responsive to few specific stimuli *Figure adopted from https://doi.org/10.1523/JNEUROSCI.4188-12.2013
  • 53. Categories of AI Chips  AI Accelerator  GPU  FPGA  ASIC  Neuromorphic chip  Network-on-Chip  Memory-based  Memristor-based  Many-core CPU  DSP  Spintronics-based  Photonics-based
  • 54. Why Neuromorphic *Figure adopted from https://bit.ly/31v1NAS
  • 55. IBM’s TrueNorth Chip *Figure adopted from https://doi.org/10.1126/science.1254642 *Video demo https://youtu.be/7ELRZrjCFd0
  • 56. Intel’s Loihi Chip *Figure adopted from https://doi.org/10.1109/MM.2018.112130359 *Video demo https://youtu.be/cDKnt9ldXv0
  • 57. BrainChip’s Akida NSoC *Figure adopted from https://www.brainchipinc.com/products/akida-neuromorphic-system-on-chip *Video demo https://bit.ly/35rea45
  • 58. 北京清華大學「天機芯」 *Video demo https://youtu.be/Nf0qVjT9WV0 *Figure adopted from https://doi.org/10.1038/s41586-019-1424-8
  • 59. ANN-to-SNN Conversion  Train ANNs using standard supervised training techniques like backpropagation to leverage the superior performance of trained ANNs and subsequently convert to event-driven SNNs for inference operation on neuromorphic platform.  Rate-encoded spikes are approximately proportional to the magnitude of the original ANN inputs.
  • 60. ANN-to-SNN Conversion (Cont’d) *Figure adopted from https://arxiv.org/abs/1802.02627 A Poisson event-generation process is used to produce the input spike train to the network.
  • 61. Software Simulation  MATLAB  PyNN http://neuralensemble.org/PyNN/  BindsNET (with PyTorch) https://github.com/Hananel-Hazan/bindsnet  Brian http://briansimulator.org/  Nengo https://www.nengo.ai/  NEST http://www.nest-simulator.org/
  • 62. Further Reading  Wulfram Gerstner & Werner M. Kistler, “Spiking Neuron Models: Single Neurons, Populations, Plasticity”. Cambridge University Press (2002)  Wulfram Gerstner, Werner M. Kistler, Richard Naud and Liam Paninski, “Neuronal Dynamics: From Single Neurons to Networks and Models of Cognition”. Cambridge University Press (2014)  Eugene M. Izhikevich, “The Dynamical Systems in Neuroscience: Geometry of Excitability and Bursting”. The MIT Press (2007)  Nikola K. Kasabov, “Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence”. Springer International Publishing (2018)  蔺想红、王向文, “脉冲神经网络原理及应用”. 科学出版社 (2018)