Statistics Is Not Formula Memorization: What Is It Deciding?
The core of statistics is judgment: describe data, estimate unknowns, compare differences, inspect associations, and make decisions under uncertainty.
learning
345 postsInference When Ghosts Are Invisible | Berkeley CS188 Topic Guide
Lectures 13–18 and Project 4 move from factor operations and variable elimination to exact inference and particle filtering, letting Pacman track invisible ghosts through noisy distance sensors.
Completing CS188: Turn 28 Lectures and Projects P0–P5 into a Portfolio | Berkeley CS188 Course Overview
Lectures 26–28 close with nuclear monitoring, AI safety, and reflection. Independent completion should preserve assumptions, test evidence, and failure analysis for Projects 1–5 instead of reporting only autograder scores.
Choosing Minimax, Alpha-Beta, and Expectimax | Berkeley CS188 Topic Guide
Lectures 5–8 use CSPs to practice variables, constraints, and search order before Project 2 implements minimax, alpha-beta, and expectimax. Their key difference is the assumption made about other agents.
From VPI and Naive Bayes to Attention | Berkeley CS188 Topic Guide
Lectures 19–25 connect rational decisions and VPI to machine learning, while Project 5 uses PyTorch for regression, classification, CNNs, attention, and an optional character-GPT.
From Value Iteration to Q-Learning | Berkeley CS188 Topic Guide
Lectures 9–12 and Project 3 use the same Gridworld to contrast value iteration with a known model, Q-learning from unknown dynamics, and approximate Q-learning that generalizes through features.
Pacman from DFS and BFS to A* | Berkeley CS188 Topic Guide
Lectures 1–4 and Project 1 connect DFS, BFS, UCS, A*, state representation, and heuristic design. The goal is not memorizing algorithms but separating what the frontier, cost, and state each control.
Learn AI Through Projects P0–P5 | Berkeley CS188 Course Overview
CS188 Spring 2026 publishes 28 recordings, 27 lecture slide sets, 11 discussions, and Projects P0–P5. P0 is a Python/autograder tutorial, P1–P4 use Pacman settings, and P5 contains general machine-learning tasks.
Spring 2025 Overview: HW1–7 with Code and Data You Can Run, Plus What Fall 2026 Looks Like | Berkeley CS189 Course Overview
CS189 exists online in several terms. From post 2 onward this series uses Spring 2026 (eecs189.org/sp26, A3) as its base, walking through each lecture block and assignment; Spring 2025 (Shewchuk) is a different classic route with 25 lectures of notes, HW1–7 and past exams, but its official recordings sit behind a bCourses login; Fall 2026 is still in progress and serves only as a reference. This post is the series entry point and full table of contents.
Exploration, RL Theory, Multitask Learning, and Open Problems | Berkeley CS285 Lectures 19–25
The final seven lectures move from exploration and theoretical limits through two review lectures to advanced exploration, multitask RL, and unresolved research problems.
The CPU, GPU, and H100 Boundary | Berkeley CS285 Topic Guide
Five assignments move from CPU-friendly imitation learning to H100-based LLM RL and six-hour offline-RL runs; self-learners should use three compute tiers instead of copying the entire enrolled workflow.
Imitation Learning, Distribution Shift, and RL Basics | Berkeley CS285 Lectures 1–4
The first four lectures move from behavioral cloning to MDPs; HW1 turns distribution shift into an observable failure through MSE policies, DAgger, and flow matching.
From Variational Inference and LLM RL to Offline RL | Berkeley CS285 Lectures 11–18
L11–18 connect control as inference, LLM RL, model-based RL, and offline RL, with HW4 and HW5 providing two compute-intensive implementations.
Policy Gradients, Actor-Critic, DQN, and SAC | Berkeley CS285 Lectures 5–10
L5–10 build the deep-RL core through policy- and value-based routes; HW2 is CPU-friendly, while HW3's Atari and HalfCheetah runs can require hours of GPU time.
Deep Reinforcement Learning: From Decision Concepts to Policy Learning and Experiments | Berkeley CS285 Course Overview
Spring 2026 CS185/285 publishes slides for 25 lectures, nine discussion units, five assignments, and starter code; lecture recordings are public on the RAIL YouTube channel, but Ed, Gradescope, and office hours remain enrolled-only, while HW4 defaults to an H100, so this is not a zero-cost open course.
Inference-time Compute, Reasoning, and Embodied Agents | Berkeley CS288 Topic Guide
Units 15–18 place NLP models inside perception, reasoning, tool, and environment loops; the question shifts from next-token prediction to allocating inference compute and validating multi-step action.
From N-grams and Word Representations to Text Classification | Berkeley CS288 Topic Guide
The first four units make text countable, representable, and classifiable; A1 then moves from n-grams and perceptrons to an NBOW MLP.
Language Models and NLP: From Foundational Representations to Retrieval and Agents | Berkeley CS288 Course Overview
CS288 moves from n-grams to RAG, reasoning, and agents through 18 public slide units and three assignments; Berkeley-only recordings make this an A3 materials route, not a public video course.
Pre-training, Post-training, Generation, and Evaluation | Berkeley CS288 Topic Guide
Units 08–12 turn a base model into an interactive system: pre-training establishes capability, post-training shapes behavior, and generation plus evaluation determine how outputs are used.
Turning Retrieval, RAG, and Advanced Architectures into a System | Berkeley CS288 Topic Guide
Units 13–14 connect models to external knowledge; A3 requires data collection, QA annotation, indexing, and ablations under CPU and latency constraints.