https://github.com/selfmadesystem/titlemlalgotest
https://github.com/selfmadesystem/titlemlalgotest
Last synced: about 1 year ago
JSON representation
- Host: GitHub
- URL: https://github.com/selfmadesystem/titlemlalgotest
- Owner: SelfMadeSystem
- License: mit
- Created: 2024-10-30T22:21:51.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-10-30T22:22:55.000Z (over 1 year ago)
- Last Synced: 2025-01-15T01:45:01.518Z (over 1 year ago)
- Language: TypeScript
- Size: 144 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Machine Learning title finder
This is a simple project that uses a machine learning model to predict the real title from a raw title. Example: `F.O.O.L & JNATHYN - Tension (Official Audio)` -> `Tension`.
## How to use
### Pre-requisites
- [bun](https://bun.sh)
- A CPU (hopefully you have one)
### Running
1. Clone the repository
2. Run `bun ./index.ts` in the terminal
3. Follow the instructions
## Built with
- [bun](https://bun.sh) - A simple and fast TypeScript runtime
- [TensorFlow.js](https://www.tensorflow.org/js) - A JavaScript library for training and deploying machine learning models in the browser and on Node.js (and subsequently bun)
## How it works
The model is a simple neural network with 3 layers. The input layer has 1 neuron for each character in the alphabet, the hidden layer has 128 neurons and the output layer has 1 neuron for each character in the alphabet. The model is trained with a dataset of 1000 titles and their respective real titles.
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.