https://github.com/EricChiang/ANN.jl
Julia artificial neural networks
https://github.com/EricChiang/ANN.jl
Last synced: 4 months ago
JSON representation
Julia artificial neural networks
- Host: GitHub
- URL: https://github.com/EricChiang/ANN.jl
- Owner: ericchiang
- License: other
- Archived: true
- Created: 2014-04-20T18:31:13.000Z (over 11 years ago)
- Default Branch: master
- Last Pushed: 2019-04-09T17:41:58.000Z (over 6 years ago)
- Last Synced: 2024-10-26T07:39:05.599Z (about 1 year ago)
- Language: Julia
- Homepage:
- Size: 205 KB
- Stars: 55
- Watchers: 6
- Forks: 11
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
- awesome-machine-master - ANN - Julia artificial neural networks (Julia)
- awesome-machine-learning - ANN - Julia artificial neural networks. **[Deprecated]** (Julia / [Tools](#tools-1))
- awesome-machine-learning - ANN - Julia artificial neural networks. (Julia / Speech Recognition)
- awesome-machine-learning - ANN - Julia artificial neural networks. **[Deprecated]** (Julia)
- awesome-julia-datasciences - ANN - Julia artificial neural networks. (APL / General-Purpose Machine Learning)
- fucking-awesome-machine-learning - ANN - Julia artificial neural networks. **[Deprecated]** (Julia / [Tools](#tools-1))
- awesome-machine-learning - ANN - Julia artificial neural networks. **[Deprecated]** (Julia / [Tools](#tools-1))
- awesome-machine-learning - ANN - Julia artificial neural networks. (Julia / Speech Recognition)
- awesome-machine-learning-cn - 官网
- awesome-machine-learning - ANN - Julia artificial neural networks. **[Deprecated]** (Julia / [Tools](#tools-1))
- awesome-advanced-metering-infrastructure - ANN - Julia artificial neural networks. (Julia / Speech Recognition)
README
julia-ann
=========
Implementation of backpropagation artificial neural networks in Julia.
Install (from within Julia interpreter):
-----------
```julia
Pkg.clone("git@github.com:EricChiang/ANN.jl.git")
```
Usage:
----------
```julia
using ANN
n_hidden_units = 20
ann = ArtificialNeuralNetwork(n_hidden_units)
n_obs = 150
n_feats = 80
X = rand(Float64, n_obs, n_feats)
y = rand(Int64, n_obs)
fit!(ann, X, y)
n_new_obs = 60
X_new = rand(Float64, n_new_obs, n_feats)
y_pred = predict(ann, X_new)
```
TODO:
-----
* Allow users to build multilayer networks
* Accept DataFrames as inputs. `fit!` and `predict` currently require Float64 matrices and vectors.