# patrick-llgc/Learning-Deep-Learning

Paper reading notes on Deep Learning and Machine Learning

Repository: https://github.com/patrick-llgc/Learning-Deep-Learning
Canonical: https://ross.abutalabs.com/products/learning-deep-learning
Language: Jupyter Notebook
License Family: other
Topics: deep-learning, paper, literature-review, machine-learning, computer-vision, cnn, paper-reading, paper-review, reinforcement-learning, medical, medical-imaging, point-cloud, 3d-object-detection, 3d-object-recognition
Last push: 2026-06-04T06:45:57+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 85, release rhythm 35, longevity 100
- inputs: {"age_days": 3440, "days_push": 90, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1269, forks 180 (observed 2026-08-28T04:04:11.621255+00:00)

## What it is
A curated collection of paper reading notes on deep learning and machine learning, with topic-organized reviews covering computer vision, 3D perception, and autonomous driving. Authored by an NVIDIA AI director, it includes starter paper lists and links to related blog posts.

## Use cases
- find deep learning papers to read as a beginner
- review notes on BEV perception for autonomous driving
- study 3D object detection and point cloud literature
- get a crash course on planning for perception engineers
- survey medical imaging and occupancy prediction papers

## When to choose
- you want curated, opinionated paper summaries rather than raw papers
- you are entering computer vision or autonomous driving research
- you need a structured first-month reading list for CNNs and deep learning

## When to avoid
- you need runnable code or production libraries
- you want exhaustive, neutral literature surveys rather than personal notes
- you need formally licensed or citable educational material (no license is provided)

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, nlp, computer-vision, machine-learning, deep-learning
- domain: deep-learning, machine-learning, computer-vision, autonomous-vehicles, tutorials
- platform: python, cross-platform
- tags: paper-notes, literature-review, autonomous-driving, bev-perception, point-cloud, medical-imaging, jupyter-notebook

## Member repositories
- patrick-llgc/Learning-Deep-Learning (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:11.621255+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 2026-08-30T05:03:33.127416+00:00, confidence not recorded.
  - readme: https://github.com/patrick-llgc/Learning-Deep-Learning (fetched 2026-08-28T04:04:11.621255+00:00, sha 43a5bead56ae)
- Data as of 2026-08-30T08:39:29.467469+00:00.