ChihebTrabelsi/deep_complex_networks

Implementation related to the Deep Complex Networks

51
/ 100
Established

This project provides code to explore and compare how different deep learning architectures, specifically those using 'complex-valued' numbers, perform on tasks like image classification and music analysis. It takes in image datasets (like CIFAR-10) or audio datasets (like MusicNet) and outputs performance metrics and visualizations, demonstrating the effectiveness of complex networks. This is intended for machine learning researchers and practitioners experimenting with novel neural network designs for specific data types.

782 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher interested in understanding or reproducing experiments with complex-valued neural networks for computer vision or audio processing.

Not ideal if you are looking for a pre-trained model or a plug-and-play solution for general image or audio classification without delving into network architecture research.

deep-learning-research computer-vision audio-processing neural-networks machine-learning-experiments
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

782

Forks

284

Language

Python

License

MIT

Last pushed

Jan 16, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ChihebTrabelsi/deep_complex_networks"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.