AI & Machine Learning

Exploring the frontiers of artificial intelligence, machine learning, and their applications

Current Focus Areas

1. Foundations: Math & Programming

AI is math-heavy, so these are the pillars.

Math:

• Linear Algebra: Khan Academy (beginner) → Strang's Introduction to Linear Algebra (deeper)
• Calculus: MIT OCW - Calculus 1–3 → especially partial derivatives & integrals
• Probability/Statistics: Introduction to Probability (MIT 6.041 SC OCW)

Programming:

• Python: Automate the Boring Stuff with Python (beginner) → then dive into Python for Data Science
• NumPy, Pandas, Matplotlib: essential for data wrangling and visualization

2. Core Machine Learning

Books:

• Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow (Aurélien Géron) → the single best practical intro
• Pattern Recognition and Machine Learning (Bishop) → more theory-heavy, grad-level

Courses:

• Andrew Ng's ML Course (Coursera) – still the gold starter
• fast.ai - Practical Deep Learning – very hands-on, project-focused

3. Deep Learning

Books:

• Deep Learning (Goodfellow, Bengio, Courville) – the "Bible"

Courses:

• DeepLearning.AI TensorFlow Developer
• Stanford CS231n: Convolutional Neural Networks for Visual Recognition – legendary
• Stanford CS224n: NLP with Deep Learning – best for language models

4. Specialization Areas

Reinforcement Learning:

• Reinforcement Learning: An Introduction (Sutton & Barto)
• DeepMind x UCL RL Lectures

NLP / Large Language Models:

• Hugging Face's Transformers Course
• Papers: "Attention Is All You Need" (Vaswani, 2017), "BERT" (Devlin, 2018), GPT papers

Generative Models:

• Generative Deep Learning (David Foster)
• Diffusion Models tutorials (Lil'Log blog, Hugging Face blog)

5. Hands-On Practice

• Kaggle – build ML projects, enter competitions
• Papers With Code – replicate cutting-edge papers with available implementations
• GitHub Projects – contribute to open-source ML repos (e.g. Hugging Face, PyTorch)

6. Staying Current

• ArXiv + ArXiv Sanity (by Andrej Karpathy) to filter papers
• Podcasts: Lex Fridman, The TWIML AI Podcast
• Twitter/X: follow AI researchers like Karpathy, Yann LeCun, François Chollet

7. Path to "Expert"

1. Start with solid math & Python
2. Do Andrew Ng + fast.ai
3. Work through Géron's book
4. Pick a specialization (vision, NLP, RL)
5. Read papers, reproduce results
6. Build projects + contribute to open source
7. Eventually, do original research or system-level engineering

Projects & Experiments

Coming soon...

Resources & Learning

• Papers and research I'm reading
• Courses and tutorials
• Interesting AI tools and frameworks

Thoughts & Insights

Random musings about AI, its future, and implications...