Pith. sign in

REVIEW

Linear discriminant initialization for feed-forward neural networks

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 2007.12782 v2 pith:522MDFWD submitted 2020-07-24 cs.LG math.MGstat.ML

classification cs.LGmath.MGstat.ML
keywords networksneuraltraininglinearaccuracyasymptoticallybasicbest
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Informed by the basic geometry underlying feed forward neural networks, we initialize the weights of the first layer of a neural network using the linear discriminants which best distinguish individual classes. Networks initialized in this way take fewer training steps to reach the same level of training, and asymptotically have higher accuracy on training data.

Discussion (0). Continue with ORCID to comment.

Pith tools