spinnaker a spiking
play

SpiNNaker: A Spiking Neural Network Architecture Petru Bogdan - PowerPoint PPT Presentation

Jan 11, 2023 •214 likes •359 views

SpiNNaker: A Spiking Neural Network Architecture Petru Bogdan petrut.bogdan@manchester.ac.uk Bio-inspiration Can massively-parallel computing resources accelerate our understanding of brain function ? Can our growing understanding of

  1. SpiNNaker: A Spiking Neural Network Architecture Petru ț Bogdan petrut.bogdan@manchester.ac.uk

  2. Bio-inspiration Can massively-parallel computing resources accelerate our understanding of brain function ? Can our growing understanding of brain function point the way to more efficient parallel, fault- tolerant computation ? Chapter 1: Origin

  3. Chip resources Chapter 2: The SpiNNaker Chip

  4. SpiNNaker Multicast routing Chapter 2: The SpiNNaker Chip

  5. SpiNNaker machines SpiNNaker board HBP platform • (864 ARM cores) – 1M cores – 11 cabinets (including server) Launch 30 March 2016 • – then 500k cores 112 remote users – 6,103 SpiNNaker jobs run – SpiNNaker chip (18 ARM cores) SpiNNaker racks (1M ARM cores) Chapter 3: Building the SpiNNaker Machines

  6. Application range Computational Neuroscience Simulation Theoretical Neurorobotics Neuroscience Chapter 5: Applications – Doing Stuff on the Machine

  7. Focus: structural plasticity for motion detection Bogdan et. al (2019, EMiT Conference) Chapter 7: Learning in neural networks Bogdan (2019, Thesis)

  8. Intuition

  9. Intuition Homogenous delays

  10. Intuition Heterogeneous delays

  11. Structural plasticity in the wild

  12. Summary • Building neuromorphic hardware to make computation more efficient , and to advance our understanding of the brain • SpiNNaker is a 1-million ARM core digital neuromorphic machine currently in use to explore theoretical and computational neuroscience simulations and neurorobotics applications • Various models of synaptic and structural plasticity are and can be implemented on this platform; digital substrate offers flexibility in exchange for efficiency • Structural plasticity is a cool learning mechanism that can be used to grow synapses with different synaptic delays to optimize neuron responses to movement

  13. Thank you! @pabmcr petrut.bogdan@manchester.ac.uk

Recommend

Supervised Learning in Structured Spiking Neural Networks 12 (including a detour to SpiNNaker)

Supervised Learning in Structured Spiking Neural Networks 12 (including a detour to SpiNNaker)

Introduction Background Our Approach Results Results SpiNNaker References Supervised Learning in Structured Spiking Neural Networks 12 (including a detour to SpiNNaker) Andr e Gr uning, Eric Nichols, Brian Gardner and Ioana Sporea

787 views • 45 slides
SpiNNaker System Software Steve Temple SpiNNaker Workshop Manchester Sep 2015 Overview

SpiNNaker System Software Steve Temple SpiNNaker Workshop Manchester Sep 2015 Overview

SpiNNaker System Software Steve Temple SpiNNaker Workshop Manchester Sep 2015 Overview SpiNNaker applications and their environment SC&MP, ybug and application loading SARK (SpiNNaker Application Runtime Kernel)

853 views • 18 slides
SpiNNaker Chip Resources Steve Temple SpiNNaker Workshop Manchester Sep 2015 Overview

SpiNNaker Chip Resources Steve Temple SpiNNaker Workshop Manchester Sep 2015 Overview

SpiNNaker Chip Resources Steve Temple SpiNNaker Workshop Manchester Sep 2015 Overview Chip Architecture Core Architecture Low-level Communication Packet formats Multicast routing High-level Communication SDP

480 views • 25 slides
Spiking Neural Networks Advanced Seminar Computer Engineering Eugen Rusakov Spiking Neural

Spiking Neural Networks Advanced Seminar Computer Engineering Eugen Rusakov Spiking Neural

Spiking Neural Networks Advanced Seminar Computer Engineering Eugen Rusakov Spiking Neural Networks Content Introduction & Motivation Human Brain Project Basics and Background Simulators Conclusion

1.59k views • 35 slides
SpiNNaker : large-scale real-time neural simulation Steve Furber ICL Professor of Computer

SpiNNaker : large-scale real-time neural simulation Steve Furber ICL Professor of Computer

SpiNNaker : large-scale real-time neural simulation Steve Furber ICL Professor of Computer Engineering The University of Manchester 1 SpiNNaker project A million mobile phone processors in one computer Able to model about 1% of the

668 views • 18 slides
Fixed-Point Maths and Libraries Michael Hopkins SpiNNaker Workshop, September 2015 Overview 1.

Fixed-Point Maths and Libraries Michael Hopkins SpiNNaker Workshop, September 2015 Overview 1.

Fixed-Point Maths and Libraries Michael Hopkins SpiNNaker Workshop, September 2015 Overview 1. Numerical calculation on SpiNNaker 2. ISO/IEC 18037 types and operations 3. A simple example 4. Some practical considerations 5. Libraries

390 views • 12 slides
An Innovative Approach to Address Spiking Karen Carraher, Executive Director, OPERS Lai Yee Woo,

An Innovative Approach to Address Spiking Karen Carraher, Executive Director, OPERS Lai Yee Woo,

An Innovative Approach to Address Spiking Karen Carraher, Executive Director, OPERS Lai Yee Woo, Senior Financial Analyst, OPERS January 28, 2013 1 Agenda Pension spiking defined Examples and statistics Contribution-Based

573 views • 33 slides
mozaik : integrative work-flow framework for large-scale spiking network simulations Jan

mozaik : integrative work-flow framework for large-scale spiking network simulations Jan

mozaik : integrative work-flow framework for large-scale spiking network simulations Jan Antolik, Andrew Davison, Yves Frgnac Unit de Neurosciences Information et Complexit, CNRS, Gif-sur-Yvette, France Motivation Most current spiking

389 views • 18 slides
Why Spiking Neural Networks Are Limited in Time (cont-d) Efficient: A Theorem Shift- and Scale-

Why Spiking Neural Networks Are Limited in Time (cont-d) Efficient: A Theorem Shift- and Scale-

Why Spiking Neural . . . Looking for Basic . . . Dependence Is . . . Simplest Possible . . . Why Spiking Neural Networks Are Limited in Time (cont-d) Efficient: A Theorem Shift- and Scale- . . . Michael Beer 1 , Julio Urenda 2 Definitions

817 views • 40 slides
The SpiNNaker Project Steve Furber ICL Professor of Computer Engineering The University of

The SpiNNaker Project Steve Furber ICL Professor of Computer Engineering The University of

The SpiNNaker Project Steve Furber ICL Professor of Computer Engineering The University of Manchester 1 200 years ago Ada Lovelace, b. 10 Dec. 1815 " I have my hopes, and very distinct ones too, of one day getting cerebral

1.54k views • 46 slides
Anti-Spiking Provisions of Chapter 32 (for Board Members) November & December, 2012 John

Anti-Spiking Provisions of Chapter 32 (for Board Members) November & December, 2012 John

Anti-Spiking Provisions of Chapter 32 (for Board Members) November & December, 2012 John Boorack Actuarial Associate Public Employee Retirement Administration Commission Chapter 176 of the Acts of 2011 Two anti-spiking provisions

483 views • 15 slides
Fast classification using sparsely active spiking networks Hesham Mostafa Institute of neural

Fast classification using sparsely active spiking networks Hesham Mostafa Institute of neural

Fast classification using sparsely active spiking networks Hesham Mostafa Institute of neural computation, UCSD Artificial networks vs. spiking networks backpropagation output layer ...... ...... Multi-layer networks are extremely hidden

431 views • 18 slides
Simula'ons of cor'cal network models made of stochas'c spiking

Simula'ons of cor'cal network models made of stochas'c spiking

Simula'ons of cor'cal network models made of stochas'c spiking neurons Antonio C. Roque Department of Physics, FFCLRP University of So Paulo, Ribeiro

579 views • 46 slides
Spinnaker Opportunities Plc A cash shell listed on London Stock Exchange, Standard List segment

Spinnaker Opportunities Plc A cash shell listed on London Stock Exchange, Standard List segment

Spinnaker Opportunities Plc A cash shell listed on London Stock Exchange, Standard List segment Company Presentation Ticker SOP SEDOL BYQC570 ISIN Number GB00BYQC5703 Disclaimer This presentation is the sole responsibility of the directors

529 views • 20 slides
Learning Beyond Finite Memory in Recurrent Networks Of Spiking Neurons Peter Ti no Ashley

Learning Beyond Finite Memory in Recurrent Networks Of Spiking Neurons Peter Ti no Ashley

Learning Beyond Finite Memory in Recurrent Networks Of Spiking Neurons Peter Ti no Ashley J.S. Mills School Of Computer Science University of Birmingham, UK Learning Beyond Finite Memory in Recurrent Networks Of Spiking Neurons Some

488 views • 24 slides
Continuous Delivery for DC/OS with Spinnaker Will Gorman @willgorman Deploying software is

Continuous Delivery for DC/OS with Spinnaker Will Gorman @willgorman Deploying software is

Continuous Delivery for DC/OS with Spinnaker Will Gorman @willgorman Deploying software is challenging Why continuous delivery? Decrease risks of deployment Decrease cost of deployment Decrease delay between feature development

643 views • 52 slides
Computationally Complete Spiking Neural P Systems Without Delay: Two Types of Neurons Are Enough

Computationally Complete Spiking Neural P Systems Without Delay: Two Types of Neurons Are Enough

Computationally Complete Spiking Neural P Systems Without Delay: Two Types of Neurons Are Enough Rudolf Freund 1 , Marian Kogler 1 , 2 1 Faculty of Informatics, Vienna University of Technology, Austria 2 Institute of Computer Science, Martin

848 views • 71 slides
Energy-Efficient Recurrent Spiking Neural Processor with Unsupervised and Supervised

Energy-Efficient Recurrent Spiking Neural Processor with Unsupervised and Supervised

Energy-Efficient Recurrent Spiking Neural Processor with Unsupervised and Supervised Spike-Timing-Dependent-Plasticity Yu Liu, Peng Li Dept. of Electrical & Computer Engineering Texas A&M University {yliu129, pli}@tamu.edu Neuromorphic

346 views • 9 slides
Learning multisensory integration with stochastic variational learning in recurrent spiking

Learning multisensory integration with stochastic variational learning in recurrent spiking

Learning multisensory integration with stochastic variational learning in recurrent spiking networks Presented by : Sharbatanu Chatterjee 1 , 2 Guided by : Aditya Gilra 1 & Johanni Brea 1 1 Laboratory of Computational Neuroscience, EPFL,

456 views • 29 slides
Effect of feedback strength in coupled spiking neural networks Javier Iglesias 1 , 2 in

Effect of feedback strength in coupled spiking neural networks Javier Iglesias 1 , 2 in

Effect of feedback strength in coupled spiking neural networks Javier Iglesias 1 , 2 in collaboration with a-Ojalvo 1 and Alessandro E.P . Villa 2 Jordi Garc 1 Departament de F sica i Enginyeria Nuclear, Universitat Polit` ecnica de

641 views • 35 slides
Too much noise to sleep: Noise-induced transition from sleep to awake-like state in a spiking

Too much noise to sleep: Noise-induced transition from sleep to awake-like state in a spiking

Too much noise to sleep: Noise-induced transition from sleep to awake-like state in a spiking network model Rodrigo F. O. Pena 1, 2 Antonio C. Roque 1 Michael A. Zaks 3 1Department of Physics, FFCLRP, University of So Paulo, Brazil

238 views • 12 slides
Event-Driven Neural Simulation Alex Rast SpiNNaker Workshop, September 2015 Session Outline 1.

Event-Driven Neural Simulation Alex Rast SpiNNaker Workshop, September 2015 Session Outline 1.

Event-Driven Neural Simulation Alex Rast SpiNNaker Workshop, September 2015 Session Outline 1. What happens When 3. Time and Events a Simulation Runs? a. Event Priorities a. Design Assumptions b. What is "Real-Time"? b. Tool Chain

567 views • 18 slides
Scalable Multi-Precision Simulation of Spiking Neural Networks on GPU with OpenCL Dmitri

Scalable Multi-Precision Simulation of Spiking Neural Networks on GPU with OpenCL Dmitri

Scalable Multi-Precision Simulation of Spiking Neural Networks on GPU with OpenCL Dmitri Yudanov (Advanced Micro Devices, USA) Leon Reznik (Rochester Institute of Technology, USA) WCCI 2012, IJCNN, June 12 Agenda Motivation OpenCL.

336 views • 16 slides
Spiking neural models: from point processes to partial differential equations. Julien Chevallier

Spiking neural models: from point processes to partial differential equations. Julien Chevallier

Spiking neural models: from point processes to partial differential equations. Julien Chevallier Co-workers: M. J. Cceres, M. Doumic and P. Reynaud-Bouret LJAD University of Nice INRIA Sophia-Antipolis 2016/06/09 Introduction Thinning

993 views • 83 slides

More recommend