Skip to content
∑ Praveen T N Learning Library
Concepts Flashcards Writing AI Feed Graph
Portfolio ↗
Overview Concepts Flashcards Writing AI Feed Graph Search Back to portfolio ↗
Library/Concepts

Concept library

638 concepts across 13 domains and 52 tracks. Each track is a coherent sequence — read it top to bottom or dip in wherever the gap is.

Clear
All domains 01Foundations 02Transformer Internals 03Training & Fine-Tuning 04Reinforcement Learning 05Inference, Systems & Hardware 06Applied LLM Engineering 07Reasoning, Evaluation & Safety 08Multimodal & Applications 09Classical ML & Statistical Learning 10Causal Inference & Experimentation 11Time Series & Forecasting 12Graphs, Recommenders & Structured Data 15Search & Information Retrieval
15

Search & Information Retrieval

Thirty years of ranking research that RAG rediscovered, usually the hard way.

4tracks
16concepts
226cards
1.9hreading
Classical Information Retrieval Inverted indexes, TF-IDF and BM25, query processing, and the lexical baselines that refuse to be beaten. 4 concepts · 60 cards
  1. 01 BM25 and Term Frequency Saturation Why a term appearing twenty times should not score ten times higher than one appearing twice, how BM25 encodes that as a saturating function, and what its two parameters actually control. intermediate 8m
  2. 02 Inverted Indexes and Postings Lists The data structure that makes text search sublinear in corpus size, why postings are stored as sorted document IDs, and how gap encoding turns a list of integers into a few bits each. intermediate 7m
  3. 03 Dynamic Pruning with WAND and Block-Max Retrieving the exact top-k without scoring most of the candidates, by maintaining an upper bound on what each document could score and skipping everything that cannot beat the current threshold. advanced 7m
  4. 04 Learned Sparse Retrieval Using a language model to assign weights over the vocabulary, including terms not present in the text, so semantic matching runs on an inverted index instead of a vector index. advanced 7m
Track overview Drill 60 cards
Learning to Rank Pointwise, pairwise and listwise objectives, LambdaMART, position bias and counterfactual training. 4 concepts · 56 cards
  1. 01 Pointwise, Pairwise and Listwise Objectives Ranking is not regression, and the three families of learning-to-rank losses differ in how much of the ranking structure they put inside the objective rather than leaving to a sort. intermediate 7m
  2. 02 Counterfactual Learning to Rank Training a ranker on logged clicks while correcting for the bias in how those clicks were generated, which turns a biased log into an unbiased estimate of a ranking objective. advanced 7m
  3. 03 LambdaRank and LambdaMART The trick of defining a gradient without ever defining a loss, which lets gradient boosting optimise a discontinuous ranking metric directly, and why the result dominated learning to rank for a decade. advanced 7m
  4. 04 Position Bias and the Examination Hypothesis Clicks measure relevance multiplied by the chance the user looked, so training on raw clicks teaches a ranker to reproduce whatever ranking generated the logs. advanced 7m
Track overview Drill 56 cards
Query Understanding Intent classification, spelling and segmentation, expansion, rewriting, and conversational query resolution. 4 concepts · 56 cards
  1. 01 Query Intent and Taxonomies The same string can be three different requests, and classifying which one determines whether the right answer is a document, an entity, an action, or a generated response. intermediate 7m
  2. 02 Spelling Correction and Query Segmentation Fixing what the user typed before matching it, where the hard part is not generating candidates but deciding whether the original was wrong at all. intermediate 7m
  3. 03 Conversational Query Rewriting Turning a context-dependent follow-up into a self-contained query, which is what lets a stateless retriever serve a stateful conversation. advanced 7m
  4. 04 Query Expansion and Pseudo-Relevance Feedback Adding terms to a query to bridge vocabulary mismatch, and the drift failure that occurs when the terms are harvested from results that were wrong to begin with. advanced 7m
Track overview Drill 56 cards
Search Evaluation Pooling and judgments, nDCG and MRR, interleaving, online metrics, and why offline gains vanish online. 4 concepts · 54 cards
  1. 01 Test Collections, Pooling and Judgment Bias The Cranfield paradigm made retrieval a measurable science, and the pooling shortcut that makes it affordable quietly penalises any system unlike the ones that built the pool. intermediate 7m
  2. 02 nDCG, MRR and Graded Relevance The main ranking metrics differ in what they assume about the user, and choosing one is choosing a model of how far someone reads and what they are looking for. intermediate 7m
  3. 03 Interleaving and Online Evaluation Mixing two rankers' results into a single list and attributing clicks gives a within-user paired comparison that detects differences far faster than an A/B test on the same traffic. advanced 7m
  4. 04 Why Offline Gains Vanish Online The recurring experience that an offline nDCG improvement produces no measurable online effect, and the four distinct mechanisms that cause it. advanced 7m
Track overview Drill 54 cards
The library

638 concepts, 6,316 flashcards and 90 long-form pieces on AI, NLP, deep learning, LLMs and agentic systems. Free, no sign-up, no paywall.

Sections Concepts Flashcards Writing AI Feed Knowledge Graph
Elsewhere Portfolio Architecture Practice RSS LinkedIn Buy me a coffee

Written and maintained by Praveen T N.

© 2026 Praveen T N