Title: Integrate and Fire Neural Network
1Integrate and Fire Neural Network
- Conceptual Chip Design
- Second draft March 27, 2006
- Computational Approaches to Cortical Functions
- The Banbury Center
Robert Shapiro Cape Visions and Global 360 Al
Davis School of Computing, University of Utah
2Objective
- Explore the possibility of using custom VLSI
chip assembly to aid in simulating large
Integrate and Fire Neural Networks - between 105 and 106 neurons.
- Current and conductance models
- Possibly exponential models
- Setup and analysis controlled by conventional
digital work station.
Very Large Scale Integrated Circuit
3Challenge
- Custom chips offer significant speed and capacity
benefits but sacrifice flexibility - Can the user community determine now the modeling
requirements current-based, conductance-based,
exponential etc. - Can we determine accuracy requirements.
- Can we determine ???
- Expected lifetime ???
4Design Decisions
- Maximize parallelism and circuit homogeneity
- parallelism both intra- and inter-chip
- Building blocks two chips (first design)
- System needs to be extensible
- of chips determine the size of the system
- Ideal performance
- roughly scale linearly with of chips
- will be sub linear
- higher stage ripple for final neural excitation
contribution - longer wires in array will lead to longer axon
excitation delay - This is a digital system for doing IAF
simulations, not an analog chip for simulating
neurons. - Speed improved by factor of 103 over conventional
digital.
5One NPU and one SPU
NPU
Dataflow
synapses contributing to a single neuron
SPU
output axon
6100 NPUs and 100 x 100 array of SPUs
NPU
NPU
SPU
SPU
SPU
SPU
7Computation for a single Neuron in NPU
Done with all spikes
How many different time constants??
Broadcast spike
Compute gex,gin
Refractory Period?
Time step size??
Compute Vinf, V
Compute spike
Increment time
Done with spikes collector
Done with spike
Start SSw
Start Sw
Start trigger
8Computation for a single Synapse in SPU
Synaptic Plasticity Habituation, Modulation and
Learning
NPU
Start Sw
Transmission delay From action potential spike to
synapse
C
W
S
Sw
Wout
synapse
A
C
9Synapse Column
Compute gex,gin
Start SSw
Start Sw
C
W
S
C
W
S
w
w
C
W
S
C
W
S
w
w
Sw
Sw
10dG
axon
V
SSw
p
q
params
start
C
W
S
C
W
S
C
W
S
C
W
S
w
w
w
w
axon
C
W
S
C
W
S
C
W
S
C
W
S
w
w
w
w
Sw
Sw
Sw
Sw
C
W
S
C
W
S
C
W
S
C
W
S
w
w
w
w
C
W
S
C
W
S
C
W
S
C
W
S
w
w
w
w
Sw
Sw
Sw
Sw
11Major Missing Pieces
- How should inputs be handled
- Membrane Potential of specific neurons set at
specific times??? - How should outputs be handled
- Spike trains must be output each spike in a time
step characterized by neuron identifier - What about spikes from/to other boards or
devices? - What software is required on digital workstation
controlling the IAF engine? - Wiring and initialization
- Input generation
- Output analysis and display
12Questions (so far)
- How important is it to make initialization fast?
- What is the range of weight values at the SPUs
- integer, fixed point, floating point??
- What is the range of firing thresholds?
- is it potentially different for each neuron?
- And many many more
13Candidate for Study
- Model of the Lateral Geniculate Nucleus and
Primary Visual Cortex - Much is known about the wiring, allowing study of
neural network dynamics with random connections
replaced by anatomical data.
14What do you Think ?
- What would this device need to do for it to be
useful in your work ?
15Acknowledgements
- Larry Abbott
- General guidance, direction and references
- Tim Vogels
- Simulation specifics, intro to neural network
models, suggestions for this presentation - Stefano Fusi
- Discussions about time step size, synaptic
plasticity, propagation delays
16Comparison with Blue Brain
- Objective
- IAF simulator, not brain
- Approach
- Design optimized to task, not a general purpose
digital computer
17Blue Brain Quotes
- For now, Markram sees the BlueGene architecture
as the best tool for modeling the brain. Blue
Brain has some 8,000 processors, and by mapping
one or two simulated brain neurons to each
processor, the computer will become a silicon
replica of 10,000 neurons. "Then we'll
interconnect them with the rules in software
that we've worked out about how the brain
functions," says Markram.
18Synapse Processing Unit
- Actions
- initialization
- set connected and weight registers
- axon spike
- if it sees a spike and is connected then weight
is placed in shift register else act as a shunt - forwards left inputs to right inputs
- intra-SPU add phase
- acts as shift register element or shunt
- shifts up on shift enabled
- Contents
- registers inhibit weight, excitation weight,
connected flag, shunt - I/Os
- tbd need to think about programming model and
need to know the range of weight values
19Neuron Processing Unit
- Actions
- initialization
- set parameters
- Start cycle
- intra-NPU add phase
- adds up shifted values and places in NPU-total
register - shifts up on shift enabled
- inter-NPU communication
- Signals completion of synapse summing and
recognizes when all neurons are finished with
spikes. - Intra-npu update phase
- membrane threshold is updated with new value in
the NPU-total register and if the threshold
exceeds the firing value then set spike flag
output axon - this involves 2 multiplies
- When all neurons finished with spike info,
broadcast new spikes - Update time
- Contents
- registers fire threshold, membrane potential,
inhibit multiplicand and current sum, excite
multiplicand and current sum, - adder, comparator, multiplier, (table for
exponential calculation in conductance model) - TBD
- number of I/Os
20Project Time Line
21ToDo
- Lots to figure out
- how many SUs will fit within area, power and I/O
constraints - circuitry is pretty trivial
- balance of parallelism vs. faster adder tradeoff
will be more tricky - vertical forwarding mechanism
- synapses will be sparsely connected
- take advantage to minimize shift register length
- Figure out done
- vertical shift registers will vary in length in
each NPU - all NPUs must be done to move to inter-NPU add
phase - inject done values on unconnected bottom lines
- ripple neuron TSU done values
- intra-NPU done will be sped up if early
completion can be figured out - maybe extra register on bottom SU to issue a done
token for intra-NPU add - ripple TSU values to emit NPU done signal?
22Excitatory Synapse Effect
gex
gex (gex SSw) x e
e expFacEx
SSw
expFacEx exp( -dt / tAMPAParam)
expFacIn exp( -dt / tGABAParam)
What about NMDA ??
23Membrane Potential Change
VRest
gain
VInf VRest gain (gEx - gIn input Theta)
gin
Vinf
gex
input
gTot gLeak gEx gIn VInf ((gLeak VRest
gEx EAMPA gIn EGABA iMagiExt) / gTot
theta
24New Membrane Potential
V
V VInf (V - Vinf) expV where expV exp( -dt
/ tau)
Vinf
expV
V VInf (V - VInf)exp((-dt/tau)gTot) Since
gTot is not a constant, this exponential must be
computed use table lookup to approximate
25Computation for a single Synapse in SPU
Swout
C Clock pulse
W weight
S synapse
Shift and add
Wout (S1 and A1) ? W 0
wout
A axon
C Clock pulse
26Sources
- Books
- The Computational Brain, Churchland and
Sejnowski, 1992 - Essentials of Neural Science and Behavior, edited
by Kandel, Schwartz and Jessell, 1995 - Pulsed Neural Networks, edited by Maass and
Bishop, 1999 - Principles of Neural Science, edited by Kandel,
Schwartz and Jessell, 2000 - Theoretical Neuroscience, Dayan and Abbott, 2001
- Spiking Neuron Models, Gerstner and Kistler, 2002
27Sources
- Articles
- Pyramidal cell communication within local
networks in layer 2/3 of rat neocortex Holmgren,
Harkany, Svennenfors and Zilberter J Physiol
(2003), 551.1, pp. 139153 - Activity dynamics and propagation of synchronous
spiking in locally connected random networks,
Mehring, Hehl, Kubo, Diesmann, Aertsen, Biol.
Cybern. 88, 395408 2003. - Mexican hats and pinwheels in visual cortex
Kang, Shelley, and Sompolinsky 28482853 PNAS
March 4, 2003 vol. 100 no. 5 - An egalitarian network model for the emergence of
simple and complex cells in visual cortex Tao,
Shelley, McLaughlin, and Shapley 366371 PNAS
January 6, 2004 vol. 101 no. 1 - Distributed High-Connectivity Network Simulation,
A. Morrison, C. Mehring, T. Geisel, A. Aertsen,
and M. Diesmann, Neural Computation 17,
17761801, 2005. - Adaptive Exponential Integrate-and-Fire Model as
an Effective Description of Neuronal Activity,
Romain Brette and Wulfram Gerstner, J
Neurophysiol 94 36373642, 2005. - Neural Network Dynamics, Tim P. Vogels, Kanaka
Rajan, and L.F. Abbott, 2005 - Signal Propagation and Logic Gating in Networks
of Integrate-And-Fire Neurons, Vogels and Abbott,
Journal of Neuroscience 2005. - Geometric and functional organization of cortical
circuits Shepherd, Stepanyants, Bureau.
Chklovskii and Svoboda June 2005 Nature
Neuroscience - Highly Nonrandom Features of Synaptic
Connectivity in Local Cortical Circuits Song,
Sjostrom, Reigl, Nelson and Chklovskii, PLoS
Biology March 2005 Volume 3 Issue 3 e68 - Excitatory cortical neurons form fine-scale
functional networks Yoshimura, Dantzker
Callaway NATURE VOL 433 24 FEBRUARY 2005