sascha-kirch/ML_Notebooks

Collection of machine learning related notebooks to share.

22
/ 100
Experimental

This collection of notebooks helps researchers and engineers understand and apply advanced signal processing and machine learning techniques. It allows you to explore how 2D Fast Fourier Transforms (FFTs) impact image reconstruction when filters are applied, or how temperature values affect softmax transformations. The collection also demonstrates adapting deep learning models for distributed training on specialized hardware like TPUs. Scientists, image processing engineers, and machine learning practitioners who work with complex signals, images, or deep neural networks would find this useful.

No commits in the last 6 months.

Use this if you need to deeply understand the practical implications of 2D FFTs on image data, experiment with softmax temperature in neural networks, or adapt TensorFlow DCGAN models for distributed training on TPUs.

Not ideal if you are looking for a plug-and-play tool for general image filtering or a high-level API for machine learning without needing to delve into the underlying mechanics.

signal-processing image-analysis deep-learning-research neural-networks scientific-computing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

19

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Sep 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sascha-kirch/ML_Notebooks"

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