Toward optimally distributed computation.

P J Edwards; A F Murray

doi:10.1162/089976698300017593

Home/Archive/PubMed

PubMed · 9573416

Toward optimally distributed computation.

P J Edwards·A F Murray

View original source ↗Export metadata ↓

Abstract

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 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 article presents regularization terms for distributing neural computation optimally.

Explore related subjects

Computer Simulation Models, Statistical Neural Networks, Computer Reproducibility of Results Journal Article Research Support, Non-U.S. Gov't

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

P J Edwards, A F Murray. 1998-05-15. Toward optimally distributed computation.. https://doi.org/10.1162/089976698300017593

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2025

Generating correlated data for omics simulation.

Simulation of realistic omics data is a key input for benchmarking studies that help users obtain optimal computational pipelines. Omics data involves large numbers of measured features on each sample and these measures are generally correlated with each other. However, simulation too often ignores these correlations, perhaps due to computational and statistical hurdles of doing so. To alleviate this, we describe three approaches for generating omics-scale data with correlated measures which mimic real datasets. These approaches are all based on a Gaussian copula approach with a covariance matrix that decomposes into a diagonal part and a low-rank part. This decomposition allows for extremely efficient simulation, overcoming a hurdle for adoption of past methods. We use these approaches to demonstrate the importance of including correlation in two benchmarking applications. First, we show that variance of results from the popular DESeq2 method increases when dependence is included. Second, we demonstrate that CYCLOPS, a method for inferring circadian time of collection from transcriptomics, improves in performance when given gene-gene dependencies in some circumstances. We provide an R package, dependentsimr, that has efficient implementations of these methods and can generate dependent data with arbitrary marginal distributions, including discrete (binary, ordered categorical, Poisson, negative binomial), continuous (normal), or with an empirical distribution.

Computer Simulation↗

PubMed2017

Addressing current challenges in cancer immunotherapy with mathematical and computational modelling.

The goal of cancer immunotherapy is to boost a patient's immune response to a tumour. Yet, the design of an effective immunotherapy is complicated by various factors, including a potentially immunosuppressive tumour microenvironment, immune-modulating effects of conventional treatments and therapy-related toxicities. These complexities can be incorporated into mathematical and computational models of cancer immunotherapy that can then be used to aid in rational therapy design. In this review, we survey modelling approaches under the umbrella of the major challenges facing immunotherapy development, which encompass tumour classification, optimal treatment scheduling and combination therapy design. Although overlapping, each challenge has presented unique opportunities for modellers to make contributions using analytical and numerical analysis of model outcomes, as well as optimization algorithms. We discuss several examples of models that have grown in complexity as more biological information has become available, showcasing how model development is a dynamic process interlinked with the rapid advances in tumour-immune biology. We conclude the review with recommendations for modellers both with respect to methodology and biological direction that might help keep modellers at the forefront of cancer immunotherapy development.

Computer Simulation↗

PubMed1999

Computer-assisted analysis of epiluminescence microscopy images of pigmented skin lesions.

BACKGROUND: Epiluminescence microscopy (ELM) is a noninvasive clinical tool recently developed for the diagnosis of pigmented skin lesions (PSLs), with the aim of improving melanoma screening strategies. However, the complexity of the ELM grading protocol means that considerable expertise is required for differential diagnosis. In this paper we propose a computer-based tool able to screen ELM images of PSLs in order to aid clinicians in the detection of lesion patterns useful for differential diagnosis. METHODS: The method proposed is based on the supervised classification of pixels of digitized ELM images, and leads to the construction of classes of pixels used for image segmentation. This process has two major phases, i.e., a learning phase, where several hundred pixels are used in order to train and validate a classification model, and an application step, which consists of a massive classification of billions of pixels (i.e., the full image) by means of the rules obtained in the first phase. RESULTS: Our results show that the proposed method is suitable for lesion-from-background extraction, for complete image segmentation into several typical diagnostic patterns, and for artifact rejection. Hence, our prototype has the potential to assist in distinguishing lesion patterns which are associated with diagnostic information such as diffuse pigmentation, dark globules (black dots and brown globules), and the gray-blue veil. CONCLUSIONS: The system proposed in this paper can be considered as a tool to assist in PSL diagnosis.

Computer Simulation↗