annex - GitLite

KO | EN

gitlite — search

#javascript #typescript #llm #machine-learning #linux #nodejs #awesome #cli #kubernetes #awesome-list #security #mcp #openai #open-source

annex

(★ 55)

Artificial Neural Networks in Elixir

File Explorer

Download Latest Version (.zip)

- annex_x.png
- annex_x.svg
- config.exs
- dev.exs
- prod.exs
- test.exs
- iris.csv
- iris.ex
- iris2.csv
- - annex_error.ex
  - cost.ex
  - data.ex
  - dataset.ex
  - debug.ex
  - defaults.ex
  - layer.ex
  - layer_config.ex
  - learner.ex
  - optimizer.ex
  - perceptron.ex
  - shape.ex
  - utils.ex
- annex.ex
- - annex_error_test.exs
  - data_test.exs
  - dataset_test.exs
  - defaults_test.exs
  - layer_config_test.exs
  - layer_test.exs
  - learner_test.exs
  - perceptron_test.exs
  - shape_test.exs
  - utils_test.exs
- - data_assertion.ex
  - data_case.ex
  - layer_case.ex
  - layer_helpers.ex
  - learner_helpers.ex
  - simple_data.ex
- and_test.exs
- annex_test.exs
- male_or_female_test.exs
- test_helper.exs
- xor2_test.exs
- xor_8_layers_test.exs
- xor_test.exs
.credo.exs
.dialyzer_ignore.exs
.formatter.exs
.gitignore
.travis.yml
CHANGELOG.md
coveralls.json
LICENSE
mix.exs
mix.lock
README.md

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<p align="center">
  <a href="https://github.com/elbow-jason/annex">
    <img alt="annex logo" src="https://raw.githubusercontent.com/elbow-jason/annex/master/assets/annex_x.png" width="160px">
  </a>
</p>

<p align="center">
  A Deep Neural Network Framework for Elixir.
</p>

<p align="center">
  <a href="https://hex.pm/packages/annex">
    <img alt="Hex Version" src="https://img.shields.io/hexpm/v/annex.svg">
  </a>
  <a href="https://hexdocs.pm/annex">
    <img alt="Hex Docs" src="https://img.shields.io/badge/hex.pm-docs-green.svg?style=flat">
  </a>
</p>
<p align="center">
  <a href="https://travis-ci.com/elbow-jason/annex">
    <img alt="TravisCI Status" src="https://travis-ci.com/elbow-jason/annex.svg?branch=master">
  </a>

<a href="https://opensource.org/licenses/MIT">
    <img alt="MIT License" src="https://img.shields.io/badge/License-MIT-blue.svg">
  </a>
</p>

<p align="center">
  <a href="https://coveralls.io/github/elbow-jason/annex?branch=master">
    <img alt="Coveralls Test Coverage Report" src="https://coveralls.io/repos/github/elbow-jason/annex/badge.svg?branch=master">
  </a>
</p>

Annex is a framework for building and executing machine learning with deep neural networks in Elixir.

## Installation

[Annex is available on Hex](https://hex.pm/packages/annex)

Annex can be installed by adding `annex` to your list of dependencies in `mix.exs`:

```elixir
def deps do
  [
    {:annex, "~> 0.2.0"}
  ]
end
```

## Features

### Layers

- [x] Sequence
  - [x] Dense
  - [x] Activation
  - [x] Dropout
  - [ ] Convolution
  - [ ] Pooling

### Data Types (Backends)

- [ ] List1D (list of floats)
  - [ ] List2D (list of lists of floats)
  - [ ] DMatrix (Dense Matrix) [dep](https://github.com/Qqwy/elixir-tensor)

## Extensions

### AnnexMatrex

- 2D Annex.Data implementor that computes at native speed.
  - Uses [BLAS](http://www.netlib.org/blas/).
  - Github: [https://github.com/elbow-jason/annex_matrex/](https://github.com/elbow-jason/annex_matrex/)
  - Dependency: [https://github.com/versilov/matrex](https://github.com/versilov/matrex)

## Media

### ElixirConf 2019 Annex Presentation by Jason Goldberger

- [YouTube](https://www.youtube.com/watch?v=Np5nSEfKLeg)
  - [Elixir Forum](https://elixirforum.com/t/elixirconf-2019-annex-introducing-an-easy-to-use-composable-deep-learning-framework-in-elixir-jason-goldberger/25189)