Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/danielholmes/neural-net
Simple Neural Net implementation in Haskell
https://github.com/danielholmes/neural-net
haskell machine-learning neural-net neural-network
Last synced: about 2 months ago
JSON representation
Simple Neural Net implementation in Haskell
- Host: GitHub
- URL: https://github.com/danielholmes/neural-net
- Owner: danielholmes
- License: bsd-3-clause
- Created: 2018-02-01T09:02:29.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2018-03-04T00:35:40.000Z (almost 7 years ago)
- Last Synced: 2024-10-30T06:27:26.782Z (3 months ago)
- Topics: haskell, machine-learning, neural-net, neural-network
- Language: Haskell
- Size: 89.8 KB
- Stars: 2
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Neural Net
[![Build Status](https://travis-ci.org/danielholmes/neural-net.svg?branch=master)](https://travis-ci.org/danielholmes/neural-net)
A simple binary classification Neural Net implementation
## Dependencies
- [Stack](https://www.haskellstack.org/)
## Setup
```bash
stack init
```## Build
```bash
stack build --pedantic
```Continuous:
```bash
stack build --pedantic --file-watch
```Only one executable:
```bash
stack build neural-net:exe:image-eg --pedantic --file-watch
```## Running Tests
```bash
stack test --pedantic
```With watching of files for changes
```bash
stack test --file-watch --pedantic
```With error stack traces
```bash
stack test --pedantic --file-watch --profile
```With more tracing
```bash
stack test --pedantic --file-watch --trace .
```## Running
```bash
stack exec neural-net-exe -- --help
```Simple Logistic Regression example:
```bash
stack exec logreg -- -c -l 0.005 -i 1000 examples/simple-csv/train.csv examples/simple-csv/test.csv
```Binary image classification Log Reg example (requires copying in some files to `/examples`):
```bash
stack exec image-logreg -- -l 0.005 -i 1000 \
examples/images/nn-course-train/1 \
examples/images/nn-course-train/0 \
examples/images/nn-course-test/1 \
examples/images/nn-course-test/0
```Binary image classification Deep NN example (requires copying in some files to `/examples`):
```bash
stack exec image-deep -- -l 0.0075 -i 2500 \
examples/images/nn-course-train/1 \
examples/images/nn-course-train/0 \
examples/images/nn-course-test/1 \
examples/images/nn-course-test/0
```## Running with Time Profiling
```bash
stack build neural-net:exe:image-deep --pedantic --profile
stack exec image-deep -- -l 0.0075 -i 2500 \
examples/images/nn-course-train/1 \
examples/images/nn-course-train/0 \
examples/images/nn-course-test/1 \
examples/images/nn-course-test/0 \
+RTS -p
```