Flashcards
11,105 cards in 101 decks, written from the same source as the concepts. Space to flip, arrows to move, K and R to sort what you know from what you do not. Progress lives in your browser.
Foundations
The mathematics and neural-network mechanics everything else assumes.
Mathematical Foundations
Linear algebra, probability, calculus and optimisation — the machinery every model is built on.
Tensors & Neural Plumbing
Shapes, matmuls, forward and backward passes, parameter counts, memory footprints.
Deep Learning Building Blocks
Convolutions, recurrence, normalisation, activations, optimisers and regularisation.
Information Theory for Language
Entropy, cross-entropy, KL, perplexity, calibration, and language modelling as compression.
Transformer Internals
Open the box. How a language model actually turns text into predictions.
Tokenisation
BPE, WordPiece, Unigram, and the ways subword vocabularies quietly shape model behaviour.
Embeddings & Representations
The lookup table, the residual stream, contextual vectors, geometry and superposition.
Attention Internals
Queries, keys and values, masking, multi-head and grouped-query, sinks, and the quadratic wall.
Positional Encoding
Sinusoidal, learned, RoPE, ALiBi, and how context windows get stretched past training length.
Transformer Anatomy
The block, the stack, encoder vs decoder, MoE, and the design choices that separate model families.
Training Objectives
Next-token prediction, masked LM, span corruption, fill-in-the-middle, and auxiliary losses.
Decoding & Generation
Greedy, beam, temperature, top-k, nucleus, and constrained generation into structured formats.
Context & In-Context Learning
Autoregressive generation, the prompt stack, context engineering, and long-context degradation.
Training & Fine-Tuning
From raw web crawl to an aligned model — data, dynamics, scale and adaptation.
Pretraining Data Pipelines
Web-scale corpus construction, filtering, deduplication, decontamination and data mixtures.
Synthetic Data
Self-Instruct, distillation, self-play, and how to generate training data without collapsing.
Training Dynamics & Scaling
Learning-rate schedules, warmup, loss spikes, critical batch size, muP, and scaling laws.
Distributed Training
Data, tensor and pipeline parallelism, ZeRO/FSDP sharding, mixed precision, and offload.
Parameter-Efficient Fine-Tuning
LoRA, QLoRA, DoRA, adapters and soft prompts — adapting big models on small budgets.
Alignment & Post-Training
SFT, reward modelling, DPO/IPO/KTO/ORPO, model merging, and evaluating an aligned model.
Reinforcement Learning
Classical RL, then the specific dialect of it that post-trains language models.
RL Foundations
MDPs, value functions, TD learning, policy gradients, actor-critic, TRPO and PPO.
RL for Language Models
RLHF as an RL problem, KL-regularised objectives, GRPO, RLVR, and reward over-optimisation.
Bandits & Exploration
Regret, UCB, Thompson sampling, contextual bandits, and exploration under a budget.
Offline & Model-Based RL
Learning from logged data, distribution shift, conservative value estimation, world models and planning.
Multi-Agent RL
Self-play, equilibria, credit assignment across agents, emergent coordination and non-stationarity.
Inference, Systems & Hardware
Where the model meets the silicon, the memory bus and the latency budget.
Inference Optimisation
KV cache, FlashAttention, speculative decoding, quantisation and continuous batching.
Accelerator Architecture
The memory wall, roofline analysis, GPU execution model, interconnects and systolic arrays.
Kernels & Compilers
CUDA, Triton, fusion, tiling, torch.compile, CUDA graphs and roofline-guided optimisation.
Serving Systems
Prompt caching, gateways and routing, token accounting, and multi-tenant isolation.
Applied LLM Engineering
Building things people use: retrieval, prompts, agents and production architecture.
Retrieval & RAG
Vector stores, hybrid retrieval and reranking, and when to retrieve instead of fine-tune.
Prompt Engineering
In-context learning, chain of thought, structured output, compression and injection-aware design.
Agents & Tool Use
Function calling, ReAct loops, MCP, agent memory architectures and evaluation harnesses.
Claude Certified Architect
Agentic loops, coordinator-subagent designs, tool interfaces and reliability patterns for Claude.
LLM Application Architecture
Routing, fallbacks, caching layers, structured state, and the reference shapes production LLM apps take.
AI for Software Engineering
Code models, repository context, patch generation, test-driven agents and SWE benchmarks.
Reasoning, Evaluation & Safety
Models that think longer, the evals that measure them, and the failure modes that matter.
Reasoning Models
Test-time compute, process reward models, the o-series, DeepSeek-R1 and contamination.
Evaluation & MLOps
Benchmarks, LLM-as-judge, red-teaming, model registries, drift detection and observability.
Safety & Alignment
Prompt injection, jailbreaks, Constitutional AI, reward hacking and mechanistic interpretability.
Multimodal & Applications
Beyond text — vision, speech, robotics and scientific discovery.
Vision & Multimodal
ViT, CLIP, diffusion, SAM, and the vision-language models that read images as tokens.
Speech Recognition
Spectrograms, CTC, RNN-T, Conformer, Whisper, streaming, diarisation and self-supervised audio.
Speech Synthesis
Acoustic models and vocoders, Tacotron, FastSpeech, HiFi-GAN, neural codecs and voice cloning.
Robotics & Embodied AI
Vision-language-action models, action tokenisation, diffusion policies and sim-to-real.
AI for Science
AlphaFold, protein language models, materials discovery, and the pitfalls of ML-for-science.
Classical ML & Statistical Learning
The statistics and non-neural models that still decide most production predictions.
Statistical Inference
Estimators, likelihood, the bootstrap, hypothesis testing, multiplicity and what a confidence interval really…
Classical Supervised Learning
Linear and logistic regression, regularisation, margins, kernels, and the geometry underneath them.
Trees & Ensembles
Impurity splitting, bagging, random forests, gradient boosting, and the engineering inside XGBoost and LightGBM.
Unsupervised Learning
Clustering, mixture models and EM, PCA and SVD, manifold embeddings, and density estimation.
Bayesian Methods
Priors and posteriors, MCMC and HMC, variational inference, Gaussian processes and model comparison.
Feature Engineering
Encoding, missingness, selection, target leakage, and the train-serve skew that eats offline gains.
Causal Inference & Experimentation
Telling correlation from cause, and measuring whether a change actually helped.
Causal Foundations
Potential outcomes, structural causal models, DAGs, confounding, colliders and the do-operator.
Online Experimentation
Power, peeking, sample ratio mismatch, variance reduction, interference and long-term effects.
Observational Causal Methods
Propensity scores, instrumental variables, difference-in-differences, regression discontinuity and synthetic …
Policy Learning & Off-Policy Evaluation
Heterogeneous treatment effects, uplift modelling, importance sampling estimators and doubly robust methods.
Time Series & Forecasting
Data with an arrow of time, where shuffling the rows destroys the problem.
Time Series Foundations
Stationarity, autocorrelation, ARIMA and state space models, seasonality and honest backtesting.
Forecasting at Scale
Hierarchical reconciliation, probabilistic forecasts, global models and time-series foundation models.
Anomaly & Changepoint Detection
Residual-based detection, CUSUM, seasonal-hybrid methods, and the base-rate problem in alerting.
Online & Streaming Learning
Incremental updates, concept drift, regret bounds, and models that must learn from a moving distribution.
Graphs, Recommenders & Structured Data
Learning over relations, catalogues and columns rather than free text.
Graph Neural Networks
Message passing, expressive power and the WL test, over-smoothing, over-squashing and sampling at scale.
Knowledge Graphs
Triples and ontologies, entity resolution, embedding-based link prediction, and grounding LLMs in structure.
Recommender Systems
Matrix factorisation, two-tower retrieval, ranking objectives, feedback loops and cold start.
Tabular Deep Learning
Why trees still win, attention over columns, prior-fitted networks and the benchmarks that decide the argument.
Generative Modelling Beyond Transformers
Diffusion, flows, adversarial games and state space models, and the theory that connects them.
Diffusion Models
Forward noising, denoising objectives, samplers, classifier-free guidance and latent diffusion.
Variational & Flow Models
The ELBO, reparameterisation, normalising flows, flow matching and rectified transport.
Adversarial Generative Models
The minimax game, mode collapse, Wasserstein critics, and what FID does and does not measure.
State Space Models
S4, Mamba, selective scan, the recurrence-convolution duality, and where linear-time sequence models pay off.
Energy-Based & Score Models
Unnormalised densities, score matching, Langevin dynamics, and the SDE view that unifies the generative families.
Efficiency, Compression & Edge AI
Making a model smaller, cheaper and local without giving away the thing that made it useful.
Quantisation
Post-training and quantisation-aware methods, outlier channels, GPTQ and AWQ, and low-bit arithmetic formats.
Knowledge Distillation
Soft targets and temperature, sequence-level and on-policy distillation, and when a student beats its teacher.
Sparsity & Pruning
Magnitude and second-order criteria, structured versus unstructured sparsity, and the hardware that rewards it.
Efficient Architectures
Small language models, depth-width tradeoffs, weight sharing, and architectures designed for a latency budget.
On-Device & Edge AI
Mobile NPUs, memory-bound inference on consumer silicon, compilation targets and privacy-driven local models.
Search & Information Retrieval
Thirty years of ranking research that RAG rediscovered, usually the hard way.
Classical Information Retrieval
Inverted indexes, TF-IDF and BM25, query processing, and the lexical baselines that refuse to be beaten.
Learning to Rank
Pointwise, pairwise and listwise objectives, LambdaMART, position bias and counterfactual training.
Query Understanding
Intent classification, spelling and segmentation, expansion, rewriting, and conversational query resolution.
Search Evaluation
Pooling and judgments, nDCG and MRR, interleaving, online metrics, and why offline gains vanish online.
Vector Databases
Index families, filtered search, freshness and deletes, sharding, and the operational reality of billion-scale ANN.
Data & Feature Engineering
The pipelines, formats and contracts that decide whether a model ever sees correct inputs.
Data Modelling & Storage
Columnar formats, table formats and the lakehouse, partitioning, and modelling choices that decide query cost.
Batch & Streaming Pipelines
Event time versus processing time, watermarks, exactly-once semantics, backfills and orchestration.
Feature Stores
Offline-online parity, point-in-time correctness, materialisation, and the failure they exist to prevent.
Data Quality & Contracts
Expectations and assertions, schema evolution, producer-consumer contracts, and detecting silent corruption.
Data Governance & Lineage
Catalogues, column-level lineage, retention and deletion, access control and provenance for training corpora.
MLOps & Platform Engineering
Everything between a notebook that works and a system that keeps working.
Experiment Tracking & Reproducibility
Run metadata, seeds and determinism, environment capture, and what it takes to rebuild a result a year later.
Model Registry & Versioning
Artefact lineage, promotion gates, rollback, and versioning models and their data together.
CI/CD for ML
Testing pipelines that emit models, data-dependent tests, progressive delivery and automated retraining.
ML Observability & Drift
Feature and prediction monitoring, delayed labels, drift statistics, and alerting that does not cry wolf.
GPU Fleet & Capacity
Scheduling and quota, fragmentation, preemption, multi-tenancy, and planning capacity under lumpy demand.
Cost & FinOps for AI
Unit economics per request, token accounting, reserved versus spot capacity, and attributing spend to features.
Security, Privacy & Adversarial ML
Attacks on models, data and the supply chain, and the defences that survive contact.
Adversarial Robustness
Perturbation attacks, adversarial training, certified defences, and the robustness-accuracy tradeoff.
Privacy-Preserving ML
Differential privacy accounting, federated learning, secure aggregation, and the utility cost of each guarantee.
LLM Application Security
Injection across trust boundaries, tool and sandbox escape, secret exposure and threat modelling for agents.
Model Provenance & Watermarking
Output watermarking, content credentials, fingerprinting weights and detecting extraction.
ML Supply Chain Security
Untrusted weights and datasets, deserialisation risk, dependency and registry attacks, and signing artefacts.
Governance, Risk & Responsible AI
Frameworks, regulation and audit evidence, treated as engineering rather than paperwork.
AI Governance Frameworks
NIST AI RMF, ISO/IEC 42001, internal review boards, and turning principles into gates that actually block.
AI Regulation & Compliance
The EU AI Act risk tiers, sectoral rules, transparency obligations and evidence a regulator will accept.
Fairness & Bias
Group and individual criteria, impossibility results, measurement under missing attributes, and mitigation costs.
Transparency & Documentation
Model and system cards, datasheets, disclosure of evaluations, and documentation that survives an audit.
AI Assurance & Audit
Third-party evaluation, red-team evidence, incident reporting, and control testing for AI systems.
Human-AI Interaction, Product & Economics
The people using the system, the product decisions around it, and what compute actually costs.
Interaction Design for AI
Latency and streaming affordances, error recovery, steering controls, and designing for probabilistic output.
AI Product Management
Scoping around uncertainty, quality bars, offline-to-online metric ladders and shipping under model drift.
Trust Calibration & Reliance
Over-reliance and automation bias, confidence display, verification cost and human-AI complementarity.
Human Data & Annotation
Guideline design, inter-annotator agreement, preference collection, rater sourcing and label noise.
Compute Economics
Capex versus tokens, utilisation and depreciation, price-performance curves and the cost floor of inference.
AI Diffusion & Labour
Adoption measurement, task-level exposure, productivity studies and what the evidence does and does not show.