BrunoVandekerkhove

BrunoVandekerkhove's Stars

• flatland/drip

  Fast JVM launching without the hassle of persistent JVMs.

  Language:Shell26712

• MLRichter/receptive_field_analysis_toolbox

  A toolbox for receptive field analysis and visualizing neural network architectures

  Language:Python1136

• jrk/gradient-halide

  Language:C++10217

• andriusstank/downhill

  Language:Haskell20

• AllenCellModeling/pytorch_fnet

  Three dimensional cross-modal image inference

  Language:Python15260

• spring-projects/spring-retry

  Language:Java2.2k519

• bgavran/Compositional_Deep_Learning

  Deep learning via category theory and functional programming

  Language:Haskell1408

• rabbitmq/rabbitmq-sharding

  Sharded logical queues for RabbitMQ: a queue type which provides improved parallelism and thoughput at the cost of total ordering

  Language:Erlang30233

• conwnet/github1s

  One second to read GitHub code with VS Code.

  Language:TypeScript22.9k876

• mhwombat/backprop-example

  An example of back-propagation implemented in Haskell.

  Language:Haskell262

• google/tangent

  Source-to-Source Debuggable Derivatives in Pure Python

  Language:Python2.3k434

• pladaria/degiro

  DEGIRO (unoficial) API

  Language:JavaScript36676

• konn/type-natural

  Type-level well-kinded natural numbers.

  Language:Haskell3312

• DataHaskell/HSVO

  Implementation of a Support Vector Machine

  Language:Haskell52

• mattjj/autodidact

  A pedagogical implementation of Autograd

  Language:Jupyter Notebook953101

• astanin/moo

  Genetic algorithm library for Haskell. Binary and continuous (real-coded) GAs. Binary GAs: binary and Gray encoding; point mutation; one-point, two-point, and uniform crossover. Continuous GAs: Gaussian mutation; BLX-α, UNDX, and SBX crossover. Selection operators: roulette, tournament, and stochastic universal sampling (SUS); with optional niching, ranking, and scaling. Replacement strategies: generational with elitism and steady state. Constrained optimization: random constrained initialization, death penalty, constrained selection without a penalty function. Multi-objective optimization: NSGA-II and constrained NSGA-II.

  Language:Haskell6013

• ajtulloch/dnngraph

  A DSL for deep neural networks, supporting Caffe and Torch

  Language:Haskell70259

• johncant/accelerate-symdiff

  Symbolic differentiation for Haskell's Accelerate

  Language:Haskell6

• pavelchristof/machine-learning

  Experiments with haskell neural networks

  Language:Haskell113

• google-research/dex-lang

  Research language for array processing in the Haskell/ML family

  Language:Haskell1.6k108

• AccelerateHS/accelerate

  Embedded language for high-performance array computations

  Language:Haskell905119

• haskell-numerics/hmatrix

  Linear algebra and numerical computation

  Language:Haskell381104

• mikeizbicki/HLearn

  Homomorphic machine learning

  Language:Haskell1.6k135

• Magalame/fastest-matrices

  Benchmark of the main linear algebra libraries in Haskell

  Language:Haskell245

• achirkin/easytensor

  Many-dimensional type-safe numeric ops

  Language:Haskell462

• jax-ml/jax

  Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

  Language:Python30.6k2.8k

• Tufte-LaTeX/tufte-latex

  A Tufte-inspired LaTeX class for producing handouts, papers, and books

  Language:TeX1.7k301

• abarbu/haskell-torch

  Practical Deep Learning in Haskell now!

  Language:Haskell501