Deep-Learning-Reference-Hub
A comprehensive collection of deep learning concepts, techniques, and best practices with mathematical foundations and practical implementations
What XERJ indexed
Snapshot
The whole repository at commit fe20a14cd0 (2026-10-17). main is 3 commits ahead.
Selected work
“add debiasing word embeddings topic and release v1.7.0”. 5 files, 1,268 lines in src/dlhub, tests, the project root.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-29. Same terms as the repository. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution
cnndeep-learningdeep-neural-networksmachine-learningpythonpytorchrnn
Example questions
- How does Deep-Learning-Reference-Hub implement cnn?
- Where does Deep-Learning-Reference-Hub handle “add debiasing word embeddings topic and release v1.7.0”?
- What does src/dlhub do in Deep-Learning-Reference-Hub?
Inside the indexed corpus
- 145 files, 2.2 MB in total, about 15.5 KB per file.
- The selected commit changed 5 of those files (3.4%).
- On GitHub since 2025-07-15, last push 2026-10-26, 134 commits on main.
- The pin is 3 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for alshawai/Deep-Learning-Reference-Hub on 2026-10-31, and the LICENSE file at commit fe20a14cd0 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Ibrahim Al-Shawa (@alshawai) has 2 selected repositories on the hub.
Their other repository pages: alshawai/PBTune.
Using XERJ with Deep-Learning-Reference-Hub
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Index a reference library for a coding agent
- ripgrep vs a code index for coding agents: 30 tasks
- Best MCP servers for local code search in 2026, compared
The prompt
Paste it into your AI agent. It clones alshawai/Deep-Learning-Reference-Hub at the pinned commit and indexes it on your machine.
Search the GitHub repository alshawai/Deep-Learning-Reference-Hub with XERJ (https://hub.xerj.org/corpus/alshawai--deep-learning-reference-hub). Run these in a shell, in order, and check each result before the next: 1. xerj --help (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh 2. git clone https://github.com/alshawai/Deep-Learning-Reference-Hub Deep-Learning-Reference-Hub && git -C Deep-Learning-Reference-Hub checkout fe20a14cd0e8b855893ac92fb4377f589f7cd8e2 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./Deep-Learning-Reference-Hub --url http://127.0.0.1:9200 --prefix deep-learning-reference --progress plain 5. xerj autoindex map --url http://127.0.0.1:9200 Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt Licence: MIT. Keep the copyright notice and credit the authors.
Related
Ibrahim Al-ShawaAI, prompts and agents corporacognitaadalflowopennyai-legal-nlpDeepLearnPhysics/spineNVIDIA/physicsnemotheomgdev/OdyssNet
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.