Weight saliency regularization in augmented networks

نویسندگان

  • Peter J. Edwards
  • Alan F. Murray
چکیده

This paper introduces the concept of “optimally distributed computation” in feed-forward neural networks via regularisation of weight saliency. By constraining the relative importance of the parameters, computation can be distributed thinly and evenly throughout the network. We propose that this will have beneficial effects on fault tolerance performance and generalisation ability in augmented network architectures. These theoretical predictions are verified by simulation experiments on two problems — one artificial and the other a “real world” task. In summary, this paper presents regularisation terms for distributing neural computation optimally.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Towards Optimally Distributed Computation

This article introduces the concept of optimally distributed computation in feedforward neural networks via regularization of weight saliency. By constraining the relative importance of the parameters, computation can be distributed thinly and evenly throughout the network. We propose that this will have beneficial effects on fault-tolerance performance and generalization ability in large netwo...

متن کامل

Task Specific Visual Saliency Prediction with Memory Augmented Conditional Generative Adversarial Networks

Visual saliency patterns are the result of a variety of factors aside from the image being parsed, however existing approaches have ignored these. To address this limitation, we propose a novel saliency estimation model which leverages the semantic modelling power of conditional generative adversarial networks together with memory architectures which capture the subject’s behavioural patterns a...

متن کامل

Towards Optimally Distributed Computation in Augmented Networks

This paper introduces the conceptof “optimally distributed computation” in feed-forward neural networks via regularisation of weight saliency. By constraining the relative importance of the parameters, computation can be distributed thinly and evenly throughout the network. We propose that this will have beneficial effects on fault tolerance performance and generalisation ability in augmented n...

متن کامل

Constraint Networks in Vision

The author has found many applications in machine vision of Constraint Networks based upon an Augmented Lagrangian formulation. This paper discusses two of the more fundamental applications: to provide a generalization of the Harris Coupled Depth-Slope analog network, and as a method of implementing data fusion (such as between two visual modules). Index Tenns-Computer vision, data fusion, neur...

متن کامل

Universal Distribution of Saliencies for Pruning in Layered Neural Networks

A better understanding of pruning methods based on a ranking of weights according to their saliency in a trained network requires further information on the statistical properties of such saliencies. We focus on two-layer networks with either a linear or nonlinear output unit, and obtain analytic expressions for the distribution of saliencies and their logarithms. Our results reveal unexpected ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1998