Pith. sign in

REVIEW 1 cited by

Effect of shapes of activation functions on predictability in the echo state network

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1905.09419 v1 pith:6BHWHV4B submitted 2019-05-22 cs.NE cs.LG

Hanten Chang , Shinji Nakaoka , Hiroyasu Ando This is my paper · ORCID
classification cs.NEcs.LG
keywords activationfunctionsechokindsstateaccuracyappropriatecompared
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We investigate prediction accuracy for time series of Echo state networks with respect to several kinds of activation functions. As a result, we found that some kinds of activation functions with an appropriate nonlinearity show high performance compared to the conventional sigmoid function.

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. Convolutional Reservoir Computing for World Models

    cs.LG 2019-07 unverdicted novelty 4.0 of 10

    RCRC uses untrained random CNNs and reservoir computing plus evolution strategies to reach claimed state-of-the-art scores in reinforcement learning tasks while avoiding data storage and heavy training.

Pith tools