Hypehttp://mloss.orgUpdates and additions to HypeenMon, 16 Nov 2015 18:35:57 -0000Hype 0.1.0<html><p>Hype is a proof-of-concept deep learning library, where you can perform optimization on compositional machine learning systems of many components, even when such components themselves internally perform optimization. </p> <p>This is enabled by nested automatic differentiation (AD) giving you access to the automatic exact derivative of any floating-point value in your code with respect to any other. Underlying computations are run by a BLAS/LAPACK backend (OpenBLAS by default). </p></html>atilim gunes baydin, barak pearlmutterMon, 16 Nov 2015 18:35:57 -0000 learningneural networksoptimizationhyperparameter