A Proposal on Machine Learning via Dynamical Systems
Communications in Mathematics and StatisticsPublished 1 March 2017
E Weinan
Citations630
SJR quartileQ3
SJR score0.43
SNIP1.08
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The idea of using continuous dynamical systems to model general high-dimensional nonlinear functions used in machine learning and the connection with deep learning is discussed.
Abstract
We discuss the idea of using continuous dynamical systems to model general high-dimensional nonlinear functions used in machine learning. We also discuss the connection with deep learning.
Keywords
Computer Science
Lecture notes in computer scienceIdentity Mappings in Deep Residual Networks
10,094 Citations2016Kaiming He, Xiangyu Zhang +2 more
The propagation formulations behind the residual building blocks suggest that the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation.
Numerical Methods for Ordinary Differential Systems: The Initial Value Problem
1,020 Citations1991J. D. Lambert
Physical Review LettersGeneralization of back-propagation to recurrent neural networks
951 Citations1987Fernando J. Pineda
An adaptive neural network with asymmetric connections is introduced that bears a resemblance to the master/slave network of Lapedes and Farber but it is architecturally simpler.
Communications in Mathematical SciencesDensity estimation by dual ascent of the log-likelihood
271 Citations2010Esteban G. Tabak, Eric Vanden‐Eijnden
A methodology is developed to assign, from an observed sample, a joint-probability distribution to a set of continuous variables, by mapping the original variables onto a jointly-Gaussian set.
Neural Information Processing SystemsGeneralization of Back propagation to Recurrent and Higher Order Neural Networks
123 Citations1987Fernando J. Pineda
A general method for deriving backpropagation algorithms for networks with recurrent and higher order networks and to a constrained dynamical system for training a content addressable memory.
Communications and control engineering/Communications and control engineering seriesMulti-dimensional Diffusion Processes
58 Citations2020Xi‐Ren Cao
The Tanaka formula is derived for multi-dimensional semi-smooth functions with the local time on the semi-Smooth curve along its gradient direction, which extends the relative optimization approach to stochastic control to multi- dimensional systems.