The Asymptotic Performance of Linear Echo State Neural Networks

03/25/2016
by   Romain Couillet, et al.
0

In this article, a study of the mean-square error (MSE) performance of linear echo-state neural networks is performed, both for training and testing tasks. Considering the realistic setting of noise present at the network nodes, we derive deterministic equivalents for the aforementioned MSE in the limit where the number of input data T and network size n both grow large. Specializing then the network connectivity matrix to specific random settings, we further obtain simple formulas that provide new insights on the performance of such networks.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

11/18/2020

Statistical model-based evaluation of neural networks

Using a statistical model-based data generation, we develop an experimen...
05/22/2017

Cost-Performance Tradeoffs in Fusing Unreliable Computational Units

We investigate fusing several unreliable computational units that perfor...
01/28/2020

MSE-Optimal Neural Network Initialization via Layer Fusion

Deep neural networks achieve state-of-the-art performance for a range of...
02/06/2012

Cramer Rao-Type Bounds for Sparse Bayesian Learning

In this paper, we derive Hybrid, Bayesian and Marginalized Cramér-Rao lo...
12/12/2021

Automatic differentiation approach for reconstructing spectral functions with neural networks

Reconstructing spectral functions from Euclidean Green's functions is an...
03/18/2021

Error Analysis of Douglas-Rachford Algorithm for Linear Inverse Problems: Asymptotics of Proximity Operator for Squared Loss

Proximal splitting-based convex optimization is a promising approach to ...
05/26/2016

Towards optimal nonlinearities for sparse recovery using higher-order statistics

We consider machine learning techniques to develop low-latency approxima...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.