lossfunctions

by @sharifshameem :)

Datasets with a data loader without a shuffle after each epoch? Generously contributed by @richardgalvez.

A highly amusing specimen from @_karfly . Truly baffles the mind.

“The Snek”, a gracious contribution from @TheReibel and Vicki :)

Evades diagnosis. Graciously contributed by @bleyddyn.

Another loss function contributed by Ray Zhang. Diagnosis impossible.

This one of a custom implementation of an RNN, graciously contributed by Ray Zhang.

Contributed by Hyun Jae Kim.

An educational post! We’re looking at the validation accuracy of a model as a function of dropout we train with. This trend is consistent with my overall experience: models with dropout train faster, but models with higher dropout win eventually. The dropout of one model is quite extreme (0.85), but it is gaining on the others! What’s going to happen as we train longer? #soexciting

 Contributed by ‏@robibok

"the slow start", contributed by Tom White.

This RNN smoothly forgets everything it has learned. God knows what happened. Contributed by Jeremy, as seen on his blog post https://jblkacademic.wordpress.com/2015/09/02/find-your-dream-job/

Taming Spatial Transformer Networks, contributed by Diogo. For the record, it’s not supposed to look like that.

A nasty-looking plateau. Sometimes. Contributed by @Luke_Metz .

“One survivor” contributed by Taco. Beautiful overfitting curves exhibiting exotic non-U shapes

Ah, the Sharp Corner Loss (SCL). Bad initialization a prime suspect.

A beautiful rainbow of learning! This code is definitely bug free. Learning rate decay might be slightly too high.