Spiking Neural Networks: The Machine Learning Approach.pdf

发布时间：2022-06-19 发布人：admin 分类：说明书资料大小：10.98M 资料格式：pdf 举报版权申诉

5a9d7473-f915-43a2-ba3a-31511bbe91d4.pdf-第1页.png

第1页 / 共84页

5a9d7473-f915-43a2-ba3a-31511bbe91d4.pdf-第2页.png

第2页 / 共84页

5a9d7473-f915-43a2-ba3a-31511bbe91d4.pdf-第3页.png

第3页 / 共84页

5a9d7473-f915-43a2-ba3a-31511bbe91d4.pdf-第4页.png

第4页 / 共84页

5a9d7473-f915-43a2-ba3a-31511bbe91d4.pdf-第5页.png

第5页 / 共84页

5a9d7473-f915-43a2-ba3a-31511bbe91d4.pdf-第6页.png

第6页 / 共84页

5a9d7473-f915-43a2-ba3a-31511bbe91d4.pdf-第7页.png

第7页 / 共84页

5a9d7473-f915-43a2-ba3a-31511bbe91d4.pdf-第8页.png

第8页 / 共84页

文本预览

Spiking Neural Networks: The Machine Learning Approach Prof.Nikola Kasabov, FIEEE, FRSNZ Knowledge Engineering and Discovery Research Institute (KEDRI), Auckland University of Technology, New Zealand nkasabov@aut.ac.nz www.kedri.info

PRESENTATION OUTLINE Content Part 1. SNN Methods Part 2. SNN Systems. STDM. Part 3. SNN Applications. Part 4. Advanced topics References SNN Methods SNN: Systems Brain Advanced Topics SNN: Applications for SSTD nkasabov@aut.ac.nz www.kedri.info

PRESENTATION OUTLINE Content Biological motivations for neurocomputation Spiking neuron models Part 1. SNN Methods 1. 2. 3. Data and information representation as spikes 4. Learning methods for SNN Part 2. SNN Systems. STDM. 5. SNN systems for pattern recognition, classification and regression 6. Neuromorphic space-time data machines. NeuCube 7. Neuromorphic hardware systems. Part 3. SNN Applications. 8. Spatio-temporal brain data 9. Audio-/ video data and moving object recognition 10. Ecological and environmental data 11. Bioinformatics 12. Predictive modelling on financial and business streaming data Part 4. Advanced topics 13. Computational neurogenetic modelling. 14. Quantum inspired evolutionary computation for SNN optimisation 15.Discussions and future directions References nkasabov@aut.ac.nz www.kedri.info

Part I: SNN Methods 1. Biological motivation for neurocomputation A single neuron is very rich of information processes: time; frequency; phase; field potentials; molecular (genetic) information; space. Three, mutually interacting, memory types - - - short term; long term genetic SNN can accommodate both spatial and temporal information as location of neurons/synapses and their spiking activity over time. nkasabov@aut.ac.nz www.kedri.info

Spiking activities of neurons Electric synaptic potentials and axonal ion channels responsible for spike generation and propagation: EPSP = excitatory postsynaptic potential, IPSP = inhibitory postsynaptic potential,  = excitatory threshold for an output spike generation. nkasabov@aut.ac.nz EPSP IPSP EPSP?IPSP   Spike train Na+ K+ Voltage-gated ion channels in the neuron membrane 

How does a synapse work? Abbreviation: NT: neurotransmitter, R : AMPA-receptor- gated ion channel for sodium, N: NMDA-receptor- gated ion channel for sodium and calcium. - Ion channels with quantum properties affect spiking activities in a stochastic way. “To spike or not to spike?” is a matter of probability. - Transmission of electric signal in a chemical synapse upon arrival of action potential into the terminal is probabilistic - Emission of a spike on the axon is also probabilistic - Prior art on stochastic modelling of neuronal processes : D. Colguhoun, B. Sakmann, E. Neher, SShoman, SWang, DTank , JHopfield nkasabov@aut.ac.nz NT R Ca2+ Ca2+ Na+ Na+ Ca2+ a b presynaptic terminal synaptic cleft postsynaptic membrane 106 m N vesicles

2. Spiking neuron models Information processing principles in SNN: – LTP and LTD – Trains of spikes – Time, frequency and space – Synchronisation and stochasticity – Evolvability… Models of a spiking neuron and SNN – Hodgkin- Huxley – Spike response model – Integrate-and-fire ----------------> – Leaky integrator – Izhikevich model – Probabilistic and neurogenetic models They offer the potential for: – Bridging neuronal functions and “lower” level genetics – Bridging spiking activities with quantum properties – Integration of modalities – Temporal or spatio-temporal data modelling nkasabov@aut.ac.nz

… Models of Spiking Neurons • Spiking neurons represent the 3rd generation of neural models, incorporating the concepts of spaceand time trough neural connectivity and plasticity • Neural modeling can be described at several levels of abstraction • Microscopic Level: Modeling of ion channels, that depend on presence/absence of various chemical messenger molecules  Hodgkin-Huxley Model  Izhikevich model  Compartment models describe small segments of a neuron separately by a set of ionic equations • Macroscopic Level: A neuron is a homogenous unit, receiving and emitting spikes according to defined internal dynamics  Integrate-and-Fire models  Probabilistic models nkasabov@aut.ac.nz

分享到：

赞收藏

资料库

Spiking Neural Networks: The Machine Learning Approach.pdf

相关推荐

人工智能

热门标签

最新资料