v0.9.5

BetaML v0.9.5

Diff since v0.9.4

• new function match_known_derivatives to set corresponding manual derivatives for well known activation or loss functions in NN and its implementation as default of the derivatives instead of nothing (i.e. AD)
• new ConvLayer and PoolLayer. while very flexible (any dimension, any function) they are way too slow for any practical work, even if the convolution ids are cached. A pitty!