# roatienza/Deep-Learning-Experiments

Videos, notes and experiments to understand deep learning

Repository: https://github.com/roatienza/Deep-Learning-Experiments
Canonical: https://ross.abutalabs.com/products/deep-learning-experiments
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: deep-learning, deep-learning-tutorial, artificial-intelligence, pytorch, vision, speech, nlp
Last push: 2026-08-15T02:54:26+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 8, longevity 100
- inputs: {"age_days": 3523, "days_push": 18, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1198, forks 768 (observed 2026-08-28T04:03:57.675376+00:00)

## What it is
A collection of deep learning lecture notes (PDFs), videos, and PyTorch Jupyter notebook experiments covering topics from MLPs and CNNs to Transformers, Mamba, and segmentation. It serves as a hands-on educational resource for understanding deep learning theory and practice.

## Use cases
- learn deep learning from scratch with pytorch notebooks
- understand how transformers work with code examples
- study mamba and state space models
- find lecture notes on cnns and rnns
- hands-on experiments for variational autoencoders
- learn image segmentation with SAM2
- supplement a university deep learning course

## When to choose
- you want theory notes paired with runnable PyTorch notebooks
- you are a student or self-learner covering classic and modern DL architectures
- you want minimal, educational implementations like Mamba on MNIST

## When to avoid
- you need production-ready model code or a maintained library
- you want a polished course platform with graded exercises
- you need large-scale training pipelines or MLOps tooling

## Facets
- artifact type: learning-resource
- maturity: active
- function: deep-learning, machine-learning, nlp, computer-vision, speech-recognition
- domain: deep-learning, machine-learning, artificial-intelligence, tutorials
- platform: python, cross-platform
- tags: jupyter-notebooks, pytorch, lecture-notes, transformers, mamba, cnn, rnn, autoencoder, self-study

## Member repositories
- roatienza/Deep-Learning-Experiments (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:57.675376+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:21:11.482995+00:00, confidence not recorded.
  - readme: https://github.com/roatienza/Deep-Learning-Experiments (fetched 2026-08-28T04:03:57.675376+00:00, sha e98c2b1952e2)
- Data as of 2026-08-30T08:39:29.467469+00:00.