Transcript DOWN - Ubiquitous Computing Lab

Soft Computing
Lecture 16
Spiking neural networks
9.11.2005
1
Phenomenology of spike generation
threshold -> Spike
j
i
Spike reception: EPSP,
summation of EPSPs
ui

Threshold Spike emission
(Action potential)
Spike reception: EPSP
9.11.2005
2
The problem of neural coding:
temporal codes
Time to first spike after input
t
correlations
Phase with respect to oscillation
9.11.2005
3
Rank Order Coding
One possibility takes advantage of the fact that a neuron can be
thought of as an analog-delay convertor. It acts somewhat like a
capacitance which is progressively charged by an input until it
reaches a threshold, at which point it generates an output pulse –
the action potential or spike.
Such neurons will naturally fire earliest when the input is strong,
and will take progressively longer to fire when the input is weaker.
In this way, the time at which a neuron fires (its response latency)
can be used to code the intensity of the stimulus.
However, this sort of code requires knowledge of when the
stimulation started, information which is not generally available in
the case of the biological visual system. There is, however, a way
round this. Consider what happens when several neurons are used
in parallel. In this case, even without knowing the precise moment
at which the stimulus came on, information can be obtained by
looking at the order in which the neurones fire
The order of firing of a group of neurons is potentially a very rich
9.11.2005
source of information about the input pattern
4
SpikeNet
• Is developed for control systems
• Features of neuron:
– Feedback from output to inputs for updating of
weights
– At summation of signals take account of frequency of
signal
– Activation function is threshold function
– Award is used for learning of neuron
• Inputs is discrete
• One-layer network from this neurons is able to
execute functions which available only for multi
layer recurrent networks
9.11.2005
5
The neural network architecture: SEQAINET
(SEQence association and Integration NETwork).
9.11.2005
6
FPGA – hardware spike neural
network for robots
9.11.2005
7
FPGA – hardware spike neural
network for robots (2)
9.11.2005
8