• No results found

A stochastic calculus approach of Learning in Spike Models

N/A
N/A
Protected

Academic year: 2021

Share "A stochastic calculus approach of Learning in Spike Models"

Copied!
8
0
0

Loading.... (view fulltext now)

Full text

(1)

A stochastic calculus approach of Learning in Spike Models Adriana Climescu-Haulica

Laboratoire de Mod´elisation et Calcul

Institute d’Informatique et Math´ematiques Appliqu´ees de Grenoble 51, rue des Math´ematiques, 38041-Grenoble cedex 9 France

email: [email protected]

Abstract

Some aspects of the Hebb’s rule are formalized by means of a SRM0

model where refractoriness and external input are neglected. Us-ing tools from stochastic calculus theory it is shown explicitly that Hebb’s rule is a 0-1 rule, based on a local learning window. As-suming the knowledge of the membrane potential, some learning inequalities are proposed, reflecting the existence of a delay on which the learning can be accomplished. The model allows a nat-ural space-time generalization.

(2)

1 The model

We consider a neuron i that receives spike input from N neurons. The membrane potential ui(t) is described by a SRM0 model (Gerstner):

ui(t) = 1 N N X j=1 Z ∞ 0 wij(t−s)(s)Sj(t−s)ds

where refractoriness and external input are neglected.

• wij(t) is the weight of the (i, j) synapse at time t

• (s) is the response kernel modelling the postsynaptic potential

• Sj is defined as

Sj(t) = X

f∈Fj

δ(t−tfj)

where Fj is the set of spiking times of the neuron j.

Using the change of variable t−s = xthe membrane potential is expressed as a stochastic integral with respect to a Poisson process

Πj(t) = X f∈Fj 1{ttf j} ui(t) = 1 N N X j=1 Z t 0 wij(x)(t−x)dΠj(x) 1 N N X j=1 X f∈Fj wij(t f j)(t−t f j)

(3)
(4)

2 0-1 Hebbian Learning rule Proposition

There is a vectorial stochastic process m(t) = (m1(t), m2(t), . . . , mN(t))

such that the conditional probability

P ( Πj(t) ∈ A | ui[0, t] = h[0, t] ) = λA( mj(h[0, t]) ) =

1 if mj(h[0, t]) ∈ A

0 if mj(h[0, t]) ∈/ A

where each component of the stochastic process m(t) is constructed by the relation mj(h[0, t]) = ∞ X k=1 1 λjkhHj(I[0, t]), e j kiL2[ √ νj(t)]hh[0, t], e j kiL2[ √ νj(t)] with Hj = p

Rju the square root functional associated with the covariance

functional of the membrane potential

Rju(h)(t) = Z t 0 Cu(t, x)h(x)d q νj(x) =HjHj∗(h)(t) the kernel Cu(t, x) = Z t∧x 0 wij(s)(t−s)wij(s)(x−s)dνj(s)

λjk and ejk are the eigenvalues and eigenvectors of the covariance functional

(5)

Definition

An interval W L = [n−D, n] is a counting window learning set asso-ciated with the spike train Sj if there is a spike time tfi for the neuron i

such that Πj(t f i) = n and Πj(t f i)−Πj(t f i −∆t) = D ≥ 1.

The Hebb’s rule become

P ( Πj(t) ∈ W L | ui[0, t] = h[0, t] ) =

1 if mj(h[0, t]) ∈ W L

0 if mj(h[0, t]) ∈/ W L

• With an a priori interpretation, the Hebb rule is a detection criterion: between the N neurons firing the neuron i which one become wired with i?

If mj(ui[0, t]) ∈ W L then the synapse (i, j) is strengthened If mj(ui[0, t]) ∈/ W L then the synapse (i, j) vanishes.

(6)

3 Learning Inequations

With an a posteriori interpretation, the Hebb rule allows the knowledge of the synaptic weights modified by a learning process.

Assume that the synapse (i, j) was strengthened. Then

n−D ≤ mj(ui[0, t]) ≤ n (1) with ( Πj(t f i) = n Πj(t f i)−Sj(t f i −∆t) = D ≥ 1

As it is known that the stochastic process mj(t) can be assimilated with a

Poisson process, the study of the inequations (1) reduces to the study of an equation ∞ X k=1 1 λjkhHj(I[0, t]), e j kiL2[ √ νj(t)]hui[0, t], e j kiL2[ √ νj(t)] = l

with l an integer value of the interval [n−D, n].

In order to determine wij(t) from the above equation, an extraction

algo-rithm is needed.

• The learning inequalities reflects the existence of a delay on which the learning can be accomplished.

(7)

4 Generalization for space-time approach

On this framework, the membrane potential can be modelled as a stochastic integral with respect to a space-time Poisson process

ui(t, x) = Z Z [O,t]×Dx wij(s, y)(t−s, x−y)dΠj(s, y) with Πj(t, x) = X f∈Fj δ(t−tfj)δ(x−xfj) Definition

An interval W L = [n−D, n] is a counting window learning set asso-ciated with the spike train Sj if there is a spike time tfi and a spike place

xfi for the neuron i such that Πj(t f i, x f i) =n and Πj(t f i, x f i)−Πj(t f i −∆t, x f i −∆x) = D ≥ 1.

The Hebb rule become

If mj (ui([0, t]×Dx)) ∈ W L then the synapse (i, j) is strengthened If mj (ui([0, t]×Dx)) ∈/ W L then the synapse (i, j) vanishes.

(8)

5 Conclusions

• The stochastic integral with respect to a Poisson process is a natural framework for spike response models.

• The Hebb rule is expressed as a detection criterion depending on the membrane potential.

• As kernels of the covariance functional of the membrane potential, the synaptic weights are involved in learning inequalities. In order to extract them, an algorithmic solution is needed.

• Space-time spiking neurons can be modelled by means of a space-time Poisson processes. The above remarks apply to space-time model as well.

References

[1] A. Climescu-Haulica, Calcul stochastique appliqu´e aux probl`emes de d´etection des signaux al´eatoires, Ph.D. Thesis, EPFL, Lausanne, 1999 [2] W. Gerstner and W.M. Kistler, Spiking Neurons Models. Single

References

Related documents

The main contribution of this study is to decrease income inequality in risk sharing network such as informal insurance through an analytical method, this study

Or, rather, a new historicity is being created, in which ‘self-determination’ policies, as well as liberal welfare policies addressing ‘disadvantage’, are designated as the

Automated theorem provers can be used to reason about all sorts of mathematical questions, and they are particularly well suited to problems of program verification, which often

extremity injuries in this age group. Central injuries have a greater incidence of strains and inflammation than upper or lower extremity injuries. 3) Tennis elbow is less frequent

Tailoring of microbial fermentations has been extensively used to increase the yield and productivities of large num- ber of bioprocesses [16].  All the tested carbon sources

Comparison of weight gain, specific growth rate and total length of shirbot, Barbus grypus larvae between experimental treatments after 21 days

(The matrix is calculated according to the coefficients reported on the upper part of table 2. For six different airline continents, the matrix shows the ratio of triggered