top | item 39386074

(no title)

bob88jg | 2 years ago

That's not what it shows at all - it shows how varying hyper parameters (which are floats and thus can be set at any arbitary precision) effects the speed at which convergence happens - so its some function F: R^n -> Z - it has literally nothing to do with the nodes in the neural network...

discuss

order

No comments yet.