QLS Guest seminar - Monday 13 November

[Quantitative Life Sciences]

QLS  guest seminar  - Monday 13 November at  11:30 ICTP, Central Area, 
2nd floor, old SISSA building, Via Beirut

Title: Learning through stochasticity in discrete neural networks

Speaker: Carlo Lucibello - Dept. of Applied Science and Technology, 
Politecnico di Torino, Turin

Abstract:
Stochasticity and limited precision of synaptic weights in neural 
network models are key aspects in both biological and hardware modeling 
of learning processes.
I'll introduce a neural network model with stochastic binary weights 
that naturally gives prominence to exponentially rare dense regions of 
solutions.
These solutions in dense regions have a number of desirable properties 
such as robustness and good generalization performance, while typical 
solutions are isolated and hard to find.
Binary solutions of the standard perceptron problem are obtained from a 
simple gradient descent procedure on a set of real values parametrizing 
a probability distribution over the binary synapses.
I'll present analytical and numerical results on the percepetron 
problem, along with algorithmic extensions aimed at training discrete 
deep neural networks.

Everyone interested is most welcome to attend!

-- 
Erica Sarnataro
Group Secretary
Quantitative Life Sciences
The Abdus Salam International Centre for Theoretical Physics (ICTP)
Trieste,  Italy
Tel. +39-040-2240623
www.ictp.it/research/qls.aspx
e-mail: qls at ictp.it