GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → o1lo01ol1o → diffhask

o1lo01ol1o / diffhask

Licence: MIT License
DSL for forward and reverse mode automatic differentiation in Haskell. Port of DiffSharp.

Programming Languages

haskell
3896 projects

Labels

deep-learningautomatic-differentiationbackpropagationdiffsharp

Projects that are alternatives of or similar to diffhask

Backprop
Heterogeneous automatic differentiation ("backpropagation") in Haskell
Stars: ✭ 154 (+492.31%)
Mutual labels:  automatic-differentiation, backpropagation
HamiltonianSolver
Numerically solves equations of motion for a given Hamiltonian function
Stars: ✭ 51 (+96.15%)
Mutual labels:  automatic-differentiation
autodiffr
Automatic Differentiation for R
Stars: ✭ 21 (-19.23%)
Mutual labels:  automatic-differentiation
Medium-Python-Neural-Network
This code is part of my post on Medium.
Stars: ✭ 58 (+123.08%)
Mutual labels:  backpropagation
YaoBlocks.jl
Standard basic quantum circuit simulator building blocks. (archived, for it is moved to Yao.jl)
Stars: ✭ 26 (+0%)
Mutual labels:  automatic-differentiation
autodiff
A .NET library that provides fast, accurate and automatic differentiation (computes derivative / gradient) of mathematical functions.
Stars: ✭ 69 (+165.38%)
Mutual labels:  automatic-differentiation
Deep-Learning-Coursera
Projects from the Deep Learning Specialization from deeplearning.ai provided by Coursera
Stars: ✭ 123 (+373.08%)
Mutual labels:  backpropagation
Quadrature.jl
A common interface for quadrature and numerical integration for the SciML scientific machine learning organization
Stars: ✭ 83 (+219.23%)
Mutual labels:  automatic-differentiation
Machine-Learning-in-Python-Workshop
My workshop on machine learning using python language to implement different algorithms
Stars: ✭ 89 (+242.31%)
Mutual labels:  backpropagation
TensorAlgDiff
Automatic Differentiation for Tensor Algebras
Stars: ✭ 26 (+0%)
Mutual labels:  automatic-differentiation
ad-lens
Automatic Differentiation using Pseudo Lenses. Neat.
Stars: ✭ 16 (-38.46%)
Mutual labels:  automatic-differentiation
AbstractOperators.jl
Abstract operators for large scale optimization in Julia
Stars: ✭ 26 (+0%)
Mutual labels:  automatic-differentiation
Learning-Lab-C-Library
This library provides a set of basic functions for different type of deep learning (and other) algorithms in C.This deep learning library will be constantly updated
Stars: ✭ 20 (-23.08%)
Mutual labels:  backpropagation
SwiftSimpleNeuralNetwork
A simple multi-layer feed-forward neural network with backpropagation built in Swift.
Stars: ✭ 29 (+11.54%)
Mutual labels:  backpropagation
bayex
Bayesian Optimization in JAX
Stars: ✭ 24 (-7.69%)
Mutual labels:  automatic-differentiation
Blur-and-Clear-Classification
Classifying the Blur and Clear Images
Stars: ✭ 88 (+238.46%)
Mutual labels:  backpropagation
dopt
A numerical optimisation and deep learning framework for D.
Stars: ✭ 28 (+7.69%)
Mutual labels:  automatic-differentiation
CS231n
PyTorch/Tensorflow solutions for Stanford's CS231n: "CNNs for Visual Recognition"
Stars: ✭ 47 (+80.77%)
Mutual labels:  backpropagation
mm-bp-snn
No description or website provided.
Stars: ✭ 30 (+15.38%)
Mutual labels:  backpropagation
tensorgrad
Differentiable Programming Tensor Networks
Stars: ✭ 102 (+292.31%)
Mutual labels:  automatic-differentiation
View All Similar Projects ➔

diffhask

Hackage Build status MIT license

Vive la programmation différentielle!

-- Yan LeCun

DSL for forward and reverse mode automatic differentiation via a version of operator overloading.

Port of DiffSharp to Haskell; currently a work in progress.

Example usage:

let g a b = (a + b / a) / (D 2.0 :: D Float)
compute $ diff' (fixPoint g (D 1.2)) (D 25.0 :: D Float) 
-- (D 1.0, D 5.0), (D 1.0, D 0.1)
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].