[HIDDEN]
Machine Learning Foundations
Core supervised learning concepts, model families, and evaluation basics.
Not published
Ai Ml And Agentic Systems
ROADMAP
25 tracks / 452 lessons
TRACKS
[HIDDEN]
Deep Learning and Neural Networks
Neural network training, deep architectures, representation learning, and deployment patterns.
Not published
[HIDDEN]
LLM Foundations
Transformer-era language modeling concepts, architectures, and capability framing.
Not published
[HIDDEN]
LLM Training, Alignment, and Serving
Training infrastructure, alignment loops, inference optimization, and deployment of large language models.
Not published
[HIDDEN]
RAG, Agents, and LLM Production
Retrieval-augmented generation, agentic systems, evaluation, and operational patterns for LLM products.
Not published
[HIDDEN]
Multimodal Foundations and Vision-Language Models
Multimodal encoders, contrastive learning, grounding, and vision-language model design.
Not published
[HIDDEN]
Reasoning and Frontier Post-Training
Synthetic data, verifiers, process supervision, reasoning traces, and frontier post-training loops.
Not published
[HIDDEN]
Agent Runtime and Tool-Use Systems
Tool schemas, planners, sandboxes, browser agents, orchestration loops, and runtime failure handling.
Not published
[HIDDEN]
Agent Memory, Planning, and Context Engineering
Episodic memory, retrieval memory, long-context strategies, context construction, and planning over state.
Not published
[HIDDEN]
World Models and Model-Based Agents
Latent dynamics, predictive state, imagination-based planning, and model-based agent architectures.
Not published
[HIDDEN]
Diffusion, Audio, Video, and Generative Media
Diffusion models, latent media generation, controllability, and evaluation across image, audio, and video systems.
Not published
[DRAFT]
Agent Safety, Guardrails, and Policy Systems
Guardrails, policy enforcement, action filtering, runtime controls, and the trust boundaries needed around agentic systems.
Not published
[DRAFT]
LLM Evaluation and Benchmarking
Offline evals, task suites, judge systems, reliability trade-offs, and the measurement discipline required to compare LLM behavior honestly.
Not published
[DRAFT]
Multi-Agent Systems and Coordination
Coordination protocols, role assignment, negotiation, and the design patterns for systems composed of multiple autonomous agents.
Not published
[DRAFT]
Tool Learning and Environment Interaction
Tool selection, environment feedback, learned interaction policies, and the mechanisms that let agents improve through action.
Not published
[DRAFT]
Causal ML and Decision Making
Interventions, counterfactual thinking, uplift, and the use of causal structure to support better decisions than prediction alone.
Not published
[DRAFT]
Optimization, Generalization, and Learning Theory
Bias-variance trade-offs, sample complexity, optimization behavior, and the theory that explains why learning succeeds or fails.
Not published
[DRAFT]
ML Systems and Training Infrastructure
Draft track for feature platforms, training pipelines, experiment systems, model deployment, and inference operations.
Not published
[DRAFT]
Probabilistic Modeling and Bayesian Inference
Latent-variable models, priors, posterior reasoning, and the probabilistic view of learning under uncertainty.
Not published
[DRAFT]
Reinforcement Learning and Sequential Decision Making
Value functions, policy learning, exploration, planning, and the algorithms for acting under delayed feedback.
Not published
[DRAFT]
Representation Learning and Self-Supervision
Embeddings, contrastive objectives, pretext tasks, and the training recipes that build reusable latent structure from raw data.
Not published
[DRAFT]
Robotics, Automation, and Embodied AI
Sensors, actuators, frames, control loops, perception, planning, safety, and simulation-to-reality gaps in embodied systems.
Not published
[DRAFT]
MLOps, DataOps, and Model Operations
Operational discipline for machine learning: datasets, training pipelines, evaluation, deployment, monitoring, drift, lineage, and rollback.
Not published
[DRAFT]
AI Research Literacy and Paper Reading
Read AI research with discipline: claims, baselines, ablations, datasets, benchmarks, limitations, replication, and implementation judgment.
Not published
[DRAFT]
Human-AI Collaboration and Agentic Workflows
Design reliable work with AI assistants and agents: delegation, context, review, tool boundaries, memory, failure recovery, and human judgment.
Not published