Start here
Machine Learning
Learn Machine Learning as a connected topic across chapters, concepts, simulations, and interview reasoning.
Machine LearningMental ModelTradeoffsFailure ModesInterview ReasoningDot Product
Begin with
Dot Product gives you the cleanest entry point before branching into constraints, failures, and related systems.
32
Chapters
10
Concepts
Related systems
Follow the nearby ideas
Use the map as a quiet orientation layer, then move back into the articles for depth.
Guidance
Machine Learning
Continues from what you have already explored.
System behavior
HyperLogLog Cardinality Estimation
Hash values route into registers, leading-zero runs update maxima, and the harmonic mean estimates unique cardinality with bounded error.
Step 1 / 3Normal flow
Read in sequence
1Dot Product in Machine Learning: The Engine Behind Similarity, Attention, and Neural NetworksTLDR: The dot product multiplies corresponding elements of two vectors and sums the results. In machine learning it does three critical jobs: it scores semantic similarity between embeddings, computes22 min2What are Logits in Machine Learning and Why They MatterTLDR: Logits are the raw, unnormalized scores produced by the final layer of a neural network — before any probability transformation. Softmax converts them to probabilities. Temperature scales them b11 min3Mathematics for Machine Learning: The Engine Under the HoodTLDR: 🚀 Three branches of math power every ML model: linear algebra shapes and transforms your data, calculus tells the model which direction to improve, and probability gives it a way to express con14 min4Machine Learning Fundamentals: A Beginner-Friendly Guide to AI ConceptsTLDR: 🤖 AI is the big umbrella, ML is the practical engine inside it, and Deep Learning is the turbo-charged rocket inside that. This guide explains -- in plain English -- how machines learn from dat15 min5Softmax Function Explained: From Raw Scores to ProbabilitiesTLDR: Softmax converts a vector of raw scores (logits) into a valid probability distribution by exponentiating each value and dividing by the total. Subtracting the max before exponentiating prevents 23 min6RAG vs Fine-Tuning: When to Use Each (and When to Combine Them)📌 TL;DR Summary
Use RAG when facts change frequently and answers must be source-grounded.
Use fine-tuning when you need stable behavior: tone, format, and domain-specific reasoning.
Use RAG + fine-t31 min7Fine-Tuning LLMs with LoRA and QLoRA: A Practical Deep-DiveTLDR: LoRA freezes the base model and trains two tiny matrices per layer — 0.1 % of parameters, 70 % less GPU memory, near-identical quality. QLoRA adds 4-bit NF4 quantization of the frozen base, enab31 min8Build vs Buy: Deploying Your Own LLM vs Using ChatGPT, Gemini, and Claude APIsTLDR: Use the API until you hit $10K/month or a hard data privacy requirement. Then add a semantic cache. Then evaluate hybrid routing. Self-hosting full model serving is only cost-effective at > 50M 31 min9Fine-Tuning LLMs: The Complete Engineer's Guide to SFT, LoRA, and RLHFTLDR: A pretrained LLM is a generalist. Fine-tuning makes it a specialist. Supervised Fine-Tuning (SFT) teaches it your domain's language through labeled examples. LoRA does the same with 99% fewer tr30 min10Transfer Learning Explained: Standing on the Shoulders of Pretrained ModelsTLDR: You don't need millions of labeled images or months of GPU time to build a great model. Transfer learning lets you borrow a pretrained network's hard-won feature detectors, plug in a new output 28 min11LLM Hallucinations: Causes, Detection, and Mitigation StrategiesTLDR: LLMs hallucinate because they are trained to predict the next plausible token — not the next true token. Understanding the three hallucination types (factual, faithfulness, open-domain) plus the30 min12Attention Mechanism Explained: How Transformers Learn to FocusTLDR: Attention lets every token in a sequence ask "what else is relevant to me?" — dynamically weighting relationships across all positions simultaneously. It replaced the fixed-size hidden-state bot25 min
Showing the top 12 of 32 matching chapters.
Related threads