The Effects of Optical Thresholding in Backpropagation Neural Networks

EC2 & Cie, 1995
Conference paper

Sigmoid-like activation functions implemented in analog hardware differ in various ways from the standard sigmoidal function as they are asymmetric, truncated, and have a non-standard gain. It is demonstrated how one can adapt the backpropagation learning rule to compensate for these non-standard sigmoids as available in hardware. This method is applied to multilayer neural networks with all-optical forward propagation and liquid crystal light valves (LCLV) as optical thresholding devices. In this paper the results of software simulations of a backpropagation neural network with five different LCLV activation functions are presented and it is shown that the adapted learning rule performs well with these LCLV curves

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related concepts

Related publications

EC2 & Cie, 1995
Conference paper

Abstract

Official source

https://infoscience.epfl.ch/record/82311?ln=en

About this result

Related concepts (7)

Related concepts

Related publications (3)

Related publications

Incorporation of Liquid-Crystal Light Valve Non-Linearities in Optical Multilayer Neural Networks

Sigmoidlike activation functions, as available in analog hardware, differ in various ways from the standard sigmoidal function because they are usually asymmetric, truncated, and have a non-standard gain. We present an adaptation of the backpropagation learning rule to compensate for these nonstandard sigmoids. This method is applied to multilayer neural networks with all-optical forward propagation and liquid-crystal light valves (LCLV) as optical thresholding devices. In this paper, the results of simulations of a backpropagation neural network with five different LCLV response curves as activation functions are presented. Although LCLV's perform poorly with the standard backpropagation algorithm, it is shown that our adapted learning rule performs well with these LCLV curves.

The Optical Society of America (OSA)1996

Results on the Steepness in Backpropagation Neural Networks

The backpropagation algorithm is widely used for training multilayer neural networks. In this publication the steepness of its activation functions is investigated. In specific, it is discussed that changing the steepness of the activation function is equivalent to changing the learning rate and the weights. Some applications of this result to optical and other hardware implementations of neural networks are given.

1994

The Interchangeability of Learning Rate and Gain in Backpropagation Neural Networks

The backpropagation algorithm is widely used for training multilayer neural networks. In this publication the gain of its activation function(s) is investigated. In specific, it is proven that changing the gain of the activation function is equivalent to changing the learning rate and the weights. This simplifies the backpropagation learning rule by eliminating one of its parameters. The theorem can be extended to hold for some well-known variations on the backpropagation algorithm, such as using a momentum term, flat spot elimination, or adaptive gain. Furthermore, it is successfully applied to compensate for the non-standard gain of optical sigmoids for optical neural networks.

MIT Press1996

Multilayer perceptron

A multilayer perceptron (MLP) is a misnomer for a modern feedforward artificial neural network, consisting of fully connected neurons with a nonlinear kind of activation function, organized in at

Backpropagation

As a machine-learning algorithm, backpropagation performs a backward pass to adjust the model's parameters, aiming to minimize the mean squared error (MSE). In a single-layered network, backpropagat

Convolutional neural network

Convolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and explodin