Skip to content

References.md

Latest commit

 

History

History
71 lines (52 loc) · 3.41 KB

References.md

File metadata and controls

71 lines (52 loc) · 3.41 KB
title References
aliases
Bibliography
Reading List
tags
references
reading
up [[MOC - Academic Paper Generation]]

References

Foundational Papers

  1. Perceptrons (1960) — Frank Rosenblatt

    • Abstract: Original work on perceptrons and neural networks
    • Relevance: Historical foundation

  2. Backpropagation (1986) — Rumelhart / Hinton / Williams

    • Abstract: Development of the backpropagation algorithm
    • Relevance: Critical for neural network training

Breakthrough Papers

  1. ImageNet Classification (2012) — Alex Krizhevsky et al.

    • Abstract: Breakthrough in deep learning with AlexNet
    • Relevance: Modern neural network success

  2. Deep Residual Learning (2015) — He et al.

    • Abstract: Residual networks for deeper models
    • Relevance: Advanced training techniques; baseline architectural prior behind many models discussed under [[MOC - Academic Paper Generation]].

Key Textbooks

  1. Neural Networks and Learning Machines (2013) — Haykin

    • Abstract: Comprehensive coverage of neural network theory
    • Relevance: Core theory

  2. Deep Learning (2016) — Goodfellow et al.

    • Abstract: Detailed guide to deep learning
    • Relevance: Advanced concepts; background for [[RLHF and RLAIF]] and [[Direct Preference Optimization]].

  3. Build a Large Language Model (From Scratch) (2024) — Sebastian Raschka

    • Abstract: End-to-end implementation of a GPT-style LLM from tokenizer through pre-training and fine-tuning.
    • Relevance: Hands-on grounding for the training-strategy notes — especially [[Structural Token Insertion]], [[Negative Sampling]], and the fine-tuning loop targeted by [[Direct Preference Optimization]].

  4. AI and Machine Learning for Coders (2020) — Laurence Moroney

    • Abstract: Practical introduction to ML/DL with TensorFlow across vision, NLP, and on-device deployment.
    • Relevance: Implementation-side companion to the more theory-heavy entries above; useful baseline reading before tackling the loss-function changes discussed in [[RLHF and RLAIF]] and [[Direct Preference Optimization]].

Free Resources

  1. MITx 6.008.1x — Introduction to computational thinking

    • Relevance: Foundational computational skills

  2. YouTube: 3Blue1Brown — Visualizations of linear algebra and neural networks

    • Relevance: Intuitive understanding of math concepts

  3. YouTube: sentdex — Practical Python for ML

    • Relevance: Hands-on implementation

Math Textbooks

  1. Linear Algebra and Its Applications (2020) — Gilbert Strang

    • Abstract: Core linear algebra for ML
    • Relevance: Matrix operations, geometry; underpins [[Embedding Cross-Sectional Similarity]].

  2. Matrix Analysis (1990) — Roger Horn, Charles Johnson

    • Abstract: Advanced matrix theory
    • Relevance: Deep mathematical foundations