Pith. sign in

REVIEW 1 cited by

Universal Approximation of Input-Output Maps by Temporal Convolutional Nets

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1906.09211 v2 pith:BXA7XHJ6 submitted 2019-06-21 cs.LG cs.SYeess.SYmath.OCstat.ML

classification cs.LGcs.SYeess.SYmath.OCstat.ML
keywords input-outputapproximationconvolutionalmapsnetworkrecurrenttcnstemporal
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

There has been a recent shift in sequence-to-sequence modeling from recurrent network architectures to convolutional network architectures due to computational advantages in training and operation while still achieving competitive performance. For systems having limited long-term temporal dependencies, the approximation capability of recurrent networks is essentially equivalent to that of temporal convolutional nets (TCNs). We prove that TCNs can approximate a large class of input-output maps having approximately finite memory to arbitrary error tolerance. Furthermore, we derive quantitative approximation rates for deep ReLU TCNs in terms of the width and depth of the network and modulus of continuity of the original input-output map, and apply these results to input-output maps of systems that admit finite-dimensional state-space realizations (i.e., recurrent models).

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Dissipation-induced Quantum Homogenization for Temporal Information Processing

    quant-ph 2024-12 reject novelty 4.0 of 10

    The authors argue the disordered quantum homogenizer is a viable reservoir computer because its dissipative dynamics converge to a steady state, but the proof is incomplete.

Pith tools