Discussion Overview
The discussion centers around the search for mathematically rigorous books on data science and neural networks, with a focus on theoretical aspects such as optimization theorems and efficient layer structures. Participants express a desire for resources that delve deeper into the mathematical foundations rather than providing superficial coverage.
Discussion Character
- Exploratory
- Technical explanation
- Debate/contested
Main Points Raised
- One participant seeks recommendations for books that emphasize mathematical rigor in data science and neural networks.
- Another participant suggests "Algorithms for Optimization" by Kochenderfer, noting its practical examples in Julia, but indicates it may not meet the desired rigor.
- Additional recommendations include Burkov's "100 page ML book" and Geron's "Hands-on ML with Scikit-Learn, Keras and Tensorflow," with a similar caveat regarding their mathematical depth.
- A participant mentions "Data Mining" by Witten et al., acknowledging its coverage but criticizing its lack of rigor compared to traditional math analysis texts.
- Another participant points out that many relevant theoretical insights are still primarily found in research papers, providing links to several arXiv papers on function approximation, gradient descent effectiveness, and error estimation.
Areas of Agreement / Disagreement
Participants generally agree on the lack of rigor in available books and the preference for more mathematically focused resources. However, there is no consensus on specific texts that fully meet the rigorous criteria sought.
Contextual Notes
Participants note the rapid development of the field may contribute to the scarcity of rigorous texts, and there is an acknowledgment that many foundational concepts are still being explored in academic papers rather than comprehensive books.