All lessons.

What AI and ML are, how learning differs from rules, and how to choose a first path.

Write small Python programs and reason about arrays, shapes, vectorization, and reproducible experiments.

Inspect real data, handle missing values, encode features, avoid leakage, and build repeatable transformations.

Understand slopes, partial derivatives, the chain rule, and gradient descent through visual and coded experiments.

Frame a problem, split data correctly, choose metrics, detect overfitting, and compare against a baseline.

Translate fairness, privacy, safety, transparency, and human oversight into testable design decisions.

Build an interpretable binary classifier using logits, sigmoid probabilities, cross-entropy, and thresholds.

Audit two candidate classifiers and defend a deployment threshold using evidence rather than one headline score.

Take a small tabular problem from question and data audit through model card, test evidence, and deployment recommendation.

Understanding randomness and Bayesian vs Frequentist views.

Normal, Binomial, and Poisson distributions.

Vectors, Matrices, Eigenvalues, and SVD.

p-values, Z-tests, and T-tests.

Lagrange multipliers, KKT optimality conditions, Slater condition, and duality.

Predicting continuous values using a linear relationship.

Hierarchical split-based classification and regression.

Combine trees with bagging and boosting, evaluate out-of-sample behavior, and diagnose feature importance safely.

Support Vector Machines for optimal boundary separation.

Unsupervised grouping of data points.

VC Dimension, Rademacher complexity, generalization error bounds, and PAC learning.

Message passing paradigms, Graph Convolutional Networks (GCN), GraphSAGE, and non-Euclidean graph representations.

The building blocks of deep learning: Perceptrons and MLPs.

How neural networks learn using the chain rule.

Backpropagation Through Time (BPTT), vanishing gradients, forget gates, and long-range sequence memory.

Convolutional Neural Networks for image recognition.

The attention mechanism that powers modern AI.

Grouped-Query Attention (GQA), Multi-Query (MQA), RoPE embeddings, and RMSNorm topology.

See how a language model predicts, selects, and appends one token at a time.

Understand how text becomes versioned token IDs, context usage, and model cost.

Learn how models represent text and how finite context changes application design.

Compare greedy decoding, temperature, and top-p through visible probability changes.

Write prompts as testable contracts with instructions, examples, data, and output rules.

Recognize unsupported output and design evidence, citations, abstention, and evaluation.

Large Language Models and the GPT architecture.

Retrieval Augmented Generation for grounding AI.

Reinforcement Learning from Human Feedback.

DeepSeek-R1 style Group Relative Policy Optimization, rule-based RL, and test-time compute.

Reasoning loops, tools, and multi-agent systems.

GANs, VAEs, and Diffusion Probabilistic Models (DDPM/DDIM).

Rectified Flow matching, optimal transport vector fields, and Patchified Diffusion Transformers (Sora/Flux).

Continuous-time SSMs, selective scan parameters, discretization, and linear-time sequence modeling.

Contrastive vision-text embeddings, InfoNCE loss, and joint cross-modal representation spaces.

Sparse routing mechanisms, gating networks, Top-K dispatch, and auxiliary load balancing.

Sparse Autoencoders (SAEs), monosemantic feature dictionaries, circuit analysis, and activation steering.

Tokenization, dense and sparse representations, similarity, ANN indexes, quantization, and rank fusion.

Context construction, prompt contracts, tool calls, schema validation, retries, and observable model APIs.

RDF triples, Turtle, OWL, SPARQL, SHACL, taxonomies, schemas, and semantic reasoning.

Chunking, query transformation, hybrid retrieval, reranking, entity resolution, and global graph search.

Ontology-constrained plans, graph-augmented reasoning, live knowledge updates, and enterprise architecture.

Clients, servers, tools, resources, prompts, transports, capability negotiation, authorization, and safe execution.

Bounded state machines, termination contracts, recovery, idempotency, budgets, no-progress detection, and replayable agent loops.

State graphs, checkpoints, working and semantic memory, durable workflows, interrupts, and multi-agent routing.

Reproducible execution, containers and microVMs, resource limits, mocks, structured observations, and trace capture.

Golden datasets, RAG and agent metrics, offline and online evaluation, regression tests, and CI release gates.

Schema controls, prompt-injection defense, least privilege, circuit breakers, budgets, approvals, and incident response.

Parallelism paradigms (DDP, TP, PP, FSDP) and scaling laws.

High-throughput LLM hosting, KV caching, vLLM, speculative decoding, and quantization.

Low-Rank Adaptation (ΔW = B·A), rank selection, FP8/INT4 uniform quantization, and scale-zero point math.

GPU HBM vs SRAM bandwidth, online softmax tiling, IO-awareness, and Triton CUDA ops.