Learning Paths

Curated study guides across all textbooks

46 paths available — click a path to view its steps.

  1. 1 Linear Algebra for AI AI Engineering Build fluency in vectors, matrices, eigendecomposition, and other linear algebra essentials for AI.
  2. 2 Probability, Statistics & Information Theory AI Engineering Study probability distributions, Bayes theorem, entropy, and KL-divergence as used in modern AI.
  3. 3 Supervised Learning AI Engineering Master regression, classification, SVMs, decision trees, and ensemble methods for supervised tasks.
  4. 4 Feature Engineering AI Engineering Learn feature selection, transformation, encoding, and dimensionality reduction techniques.
  5. 5 Neural Networks from Scratch AI Engineering Implement feedforward neural networks from the ground up, including backpropagation and gradient descent.
  6. 6 Convolutional Neural Networks AI Engineering Understand CNN architectures for image recognition, object detection, and visual feature extraction.
  7. 7 The Attention Mechanism AI Engineering Explore self-attention, multi-head attention, and how attention revolutionized sequence modeling.
  8. 8 The Transformer Architecture AI Engineering Dive deep into the encoder-decoder transformer, positional encodings, and why transformers dominate NLP.
  9. 9 Scaling Laws and Large Language Models AI Engineering Study neural scaling laws, emergent abilities, and the engineering behind training frontier LLMs.
  10. 10 Fine-Tuning LLMs AI Engineering Learn LoRA, QLoRA, instruction tuning, and RLHF techniques for adapting large language models.
  11. 11 Neural Networks from Scratch
  12. 12 Convolutional Neural Networks
  13. 13 The Transformer Architecture
  1. 1 Python Fundamentals for Sports NFL Analytics Set up your Python environment and learn pandas, numpy, and data wrangling for sports analysis.
  2. 2 Statistical Foundations for Sports Soccer Analytics Ground yourself in hypothesis testing, regression, and statistical inference applied to soccer data.
  3. 3 Data Visualization Fundamentals College Football Analytics Create publication-quality charts and plots to communicate analytical findings effectively.
  4. 4 Expected Goals (xG) Modeling Soccer Analytics Build expected goals models from shot-level data, the foundational metric of modern soccer analytics.
  5. 5 Shot Quality Models in Basketball Basketball Analytics Develop shot quality models using spatial data, defender proximity, and game context features.
  6. 6 Machine Learning Prediction NFL Analytics Apply random forests, gradient boosting, and other ML algorithms to predict NFL game outcomes.
  7. 7 Neural Networks for Sports Betting Sports Betting Train neural networks for point spread prediction, player prop modeling, and market forecasting.
  8. 8 Computer Vision in Soccer Soccer Analytics Apply computer vision techniques to video data for player tracking, event detection, and tactical analysis.
  9. 9 Advanced ML in Basketball Basketball Analytics Use advanced machine learning for lineup optimization, draft modeling, and season projection systems.
  10. 10 Vision Transformers AI Engineering Study Vision Transformers (ViT) and learn how transformer architectures are applied to sports video and image analysis.
  11. 11 Python Tools for Soccer Analytics
  12. 12 Data Sources and Collection
  13. 13 Introduction to Predictive Analytics in Football
  1. 1 The Transformer Architecture AI Engineering Understand the transformer architecture that powers every modern AI coding assistant.
  2. 2 Scaling Laws & Large Language Models AI Engineering Study how scaling laws govern LLM capabilities and why bigger models produce better code.
  3. 3 Prompt Engineering (AI Theory) AI Engineering Learn the theoretical foundations of prompt engineering — few-shot learning, chain-of-thought, and instruction following.
  4. 4 AI Agents & Tool Use AI Engineering Understand agent architectures, tool use, and how AI systems interact with external environments.
  5. 5 Prompt Engineering for Code Vibe Coding Apply prompt engineering theory to practical code generation with AI coding assistants.
  6. 6 Advanced Prompting Techniques Vibe Coding Master advanced prompting strategies including chain-of-thought coding, constraint specification, and meta-prompting.
  7. 7 AI Coding Agents Vibe Coding Work with autonomous AI coding agents that plan, execute, and iterate on complex software tasks.
  8. 8 Custom Tools & MCP Servers Vibe Coding Build custom tools and MCP servers to extend AI coding agents with domain-specific capabilities.
  9. 9 Multi-Agent Systems Vibe Coding Orchestrate multiple AI agents working together on complex software development projects.
  10. 10 Building AI-Powered Apps Vibe Coding Build applications that integrate LLMs as core features — chatbots, RAG systems, and AI-native software.
  11. 11 Emerging Frontiers Vibe Coding Explore the cutting edge of AI-assisted development — what's coming next and how to stay ahead.
  12. 12 How Language Models Think
  13. 13 Advanced Prompting Techniques
  14. 14 Capstone Projects
  1. 1 How Memory Works Metacognition Understand the architecture of human memory and how information is encoded, stored, and retrieved.
  2. 2 Why We Forget Metacognition Learn the science behind forgetting and why it is actually essential to the learning process.
  3. 3 Cognitive Load and Its Limits Metacognition Discover why your working memory has hard limits and how to design study sessions around them.
  4. 4 Learning Strategies That Actually Work Metacognition Survey the evidence-based strategies — retrieval practice, spaced repetition, interleaving — that outperform rereading and highlighting.
  5. 5 Learning Myths Debunked Metacognition Separate fact from fiction on learning styles, multitasking, left-brain/right-brain, and other popular myths.
  6. 6 Desirable Difficulties Metacognition Learn why making studying harder in the right ways leads to deeper, more durable learning.
  7. 7 Metacognitive Monitoring Metacognition Develop the skill of accurately assessing what you know and what you don't — the foundation of self-directed learning.
  8. 8 Self-Testing as a Learning Tool Metacognition Use practice testing not just for assessment but as one of the most powerful learning strategies available.
  9. 9 How to Read for Deep Understanding Metacognition Transform passive reading into active comprehension using evidence-based reading strategies.
  10. 10 Building Your Learning Operating System Metacognition Integrate everything into a personal learning system you can use for the rest of your life.
  11. 11 Metacognition — Thinking About Your Own Thinking
  12. 12 Retrieval Practice
  13. 13 Desirable Difficulties
  1. 1 Introduction to Cross-Domain Thinking Pattern Recognition Understand why the same deep structures keep appearing across wildly different fields.
  2. 2 Feedback Loops Pattern Recognition Recognize positive and negative feedback loops and how they drive growth, stability, and collapse.
  3. 3 Emergence Pattern Recognition See how simple rules produce complex, unpredictable behavior — from ant colonies to stock markets.
  4. 4 Power Laws Pattern Recognition Learn why extreme events are far more common than normal distributions predict, and what that means for planning.
  5. 5 Phase Transitions Pattern Recognition Understand how systems flip suddenly from one state to another — and why gradual change can mask approaching tipping points.
  6. 6 Distributed vs. Centralized Systems Pattern Recognition Compare the tradeoffs between centralized control and distributed networks in organizations, ecosystems, and software.
  7. 7 Redundancy and Resilience Pattern Recognition Discover why apparent inefficiency — redundant systems, slack resources — is often the key to surviving shocks.
  8. 8 Cascading Failures Pattern Recognition Trace how small failures propagate through tightly coupled systems to produce catastrophic outcomes.
  9. 9 Scaling Laws Pattern Recognition Explore the mathematical relationships that govern how systems change as they grow — from cities to organisms to companies.
  10. 10 The S-Curve Pattern Recognition Recognize the ubiquitous S-shaped growth pattern and learn to identify where you are on the curve.
  11. 11 How to Think Across Domains Pattern Recognition Build a personal practice for spotting patterns, transferring mental models, and thinking in systems.
  12. 12 How to Think Across Domains
  13. 13 The Pattern Atlas
  1. 1 Calibration: Knowing What You Know Metacognition Learn to align your confidence with your actual accuracy — the single most important metacognitive skill for decision-making.
  2. 2 Metacognitive Monitoring Metacognition Develop the habit of stepping back to evaluate your own thinking processes in real time.
  3. 3 Motivation and Self-Regulation Metacognition Understand how motivation biases your reasoning and learn strategies for staying intellectually honest.
  4. 4 Goodhart's Law Pattern Recognition Discover why optimizing for a measure inevitably corrupts it — and how this trap undermines organizations everywhere.
  5. 5 Survivorship Bias Pattern Recognition Learn to see the data that is missing — the failures, the silent evidence, the stories that never get told.
  6. 6 Narrative Capture Pattern Recognition Recognize how compelling stories hijack your reasoning and lead you to ignore contradictory evidence.
  7. 7 Chesterton's Fence Pattern Recognition Before tearing something down, understand why it was built — a principle for avoiding unintended consequences.
  8. 8 The Map Is Not the Territory Pattern Recognition Understand the gap between models and reality, and learn when to trust (and distrust) abstractions.
  9. 9 How Brains Misread Luck Science of Luck Explore the cognitive biases that cause us to see patterns in randomness and misattribute outcomes to skill.
  10. 10 Emotional Intelligence in Decisions Applied Psychology Learn how emotions shape your judgments and how emotional intelligence improves decision quality.
  11. 11 Metacognition — Thinking About Your Own Thinking
  12. 12 The Humility Chapter
  1. 1 The World of COBOL Learning COBOL Discover why COBOL still powers the global economy and begin your journey into mainframe programming.
  2. 2 COBOL Program Structure Learning COBOL Learn the four divisions of a COBOL program and write your first working program.
  3. 3 Conditional Logic Learning COBOL Master IF/ELSE, EVALUATE, and condition handling to build decision-making programs.
  4. 4 Sequential File Processing Learning COBOL Learn to read and write sequential files, the backbone of batch processing on mainframes.
  5. 5 COBOL Program Structure Deep Dive Intermediate COBOL Deepen your understanding of COBOL program architecture and advanced division features.
  6. 6 CALL and Subprogram Linkage Intermediate COBOL Build modular COBOL applications using CALL statements and subprogram linkage conventions.
  7. 7 Embedded SQL Fundamentals Intermediate COBOL Connect COBOL programs to DB2 databases using embedded SQL for enterprise data access.
  8. 8 The z/OS Ecosystem Advanced COBOL Understand the z/OS mainframe ecosystem and how COBOL fits into enterprise architecture.
  9. 9 CICS Architecture Advanced COBOL Master CICS transaction server architecture for building online mainframe applications.
  10. 10 DB2 Optimizer Deep Dive Advanced COBOL Learn how the DB2 optimizer works to write high-performance COBOL-DB2 programs.
  11. 11 Mainframe Security Advanced COBOL Understand RACF, security models, and compliance requirements for enterprise mainframe systems.
  12. 12 Modernization Strategy Advanced COBOL Explore strategies for modernizing legacy COBOL systems while preserving business logic.
  13. 13 COBOL Career Guide and the Path Forward
  14. 14 Debugging Techniques and Tools
  15. 15 The COBOL Landscape Today
  1. 1 What is Data Science? Intro to Data Science Explore the data science landscape, career paths, and the tools used by data scientists.
  2. 2 Python Fundamentals for Data Science Intro to Data Science Learn core Python programming concepts tailored for data analysis workflows.
  3. 3 Introduction to pandas Intro to Data Science Master the pandas library for loading, exploring, and manipulating tabular data.
  4. 4 Cleaning Messy Data Intro to Data Science Learn techniques for handling missing values, duplicates, and inconsistent data.
  5. 5 Matplotlib Foundations Intro to Data Science Create informative charts and graphs to visualize patterns in your data.
  6. 6 Graphs and Descriptive Statistics Introductory Statistics Build a statistical foundation with histograms, box plots, and summary measures.
  7. 7 Probability Foundations Introductory Statistics Learn probability rules and how they underpin statistical inference and prediction.
  8. 8 Descriptive Statistics in Python Intro to Data Science Compute and interpret descriptive statistics using Python for real-world datasets.
  9. 9 Hypothesis Testing Intro to Data Science Apply hypothesis testing to make data-driven decisions with statistical confidence.
  10. 10 Linear Regression Intro to Data Science Build your first predictive model using linear regression and interpret its results.
  11. 11 Decision Trees and Random Forests Intro to Data Science Learn tree-based models for classification and regression tasks.
  12. 12 Evaluating Models Intro to Data Science Master metrics and validation techniques to assess how well your models perform.
  13. 13 Data Wrangling: Cleaning and Preparing Real Data
  14. 14 Cleaning and Preparing Data for Analysis
  15. 15 Communicating with Data
  1. 1 Why Statistics Matters Introductory Statistics Understand why statistical literacy is essential for making sense of data in any field.
  2. 2 Types of Data Introductory Statistics Learn to distinguish categorical, ordinal, and numerical data types and their implications.
  3. 3 Graphs and Descriptive Statistics Introductory Statistics Visualize data distributions with histograms, box plots, and stem-and-leaf displays.
  4. 4 Numerical Summaries Introductory Statistics Calculate and interpret measures of center, spread, and position.
  5. 5 Probability Foundations Introductory Statistics Learn probability rules, counting methods, and how to reason about random events.
  6. 6 Probability Distributions and the Normal Curve Introductory Statistics Understand discrete and continuous distributions, with a focus on the normal distribution.
  7. 7 Confidence Intervals Introductory Statistics Construct and interpret confidence intervals to estimate population parameters.
  8. 8 Hypothesis Testing Introductory Statistics Learn the logic of hypothesis testing, p-values, and how to draw conclusions from data.
  9. 9 Correlation and Simple Regression Introductory Statistics Explore relationships between variables using correlation and linear regression models.
  10. 10 Correlation and Causation in Python Intro to Data Science Apply statistical concepts in Python to distinguish correlation from causation in real datasets.
  11. 11 Distributions and the Normal Curve
  12. 12 Sampling Distributions and the Central Limit Theorem
  13. 13 Inference for Means
  1. 1 Variables, Types, and Expressions Intro CS Python Master Python fundamentals including variables, data types, and expressions.
  2. 2 Functions Intro CS Python Learn to write reusable functions that form the building blocks of data pipelines.
  3. 3 Lists and Tuples Intro CS Python Work with Python's core sequence types to organize and process data collections.
  4. 4 Introduction to pandas Python for Business Discover pandas DataFrames and Series for business data analysis workflows.
  5. 5 Cleaning and Preparing Data Python for Business Learn practical techniques for cleaning messy real-world business data.
  6. 6 Transforming and Aggregating Data Python for Business Master groupby, pivot tables, and aggregation for summarizing business metrics.
  7. 7 Data Visualization with matplotlib Python for Business Create publication-quality charts to communicate data insights effectively.
  8. 8 Reshaping and Transforming Data Intro to Data Science Learn advanced data reshaping techniques including melting, pivoting, and merging.
  9. 9 Seaborn Statistical Visualization Intro to Data Science Build statistical visualizations with seaborn for exploratory data analysis.
  10. 10 What is a Model? Intro to Data Science Understand the fundamentals of statistical and machine learning models.
  11. 11 Linear Regression Intro to Data Science Build predictive models using linear regression and scikit-learn.
  12. 12 The ML Workflow Intro to Data Science Master the complete machine learning workflow from data preparation to model deployment.
  13. 13 Introduction to pandas
  14. 14 Your First Data Analysis
  15. 15 Loading and Exploring Real Business Datasets
  1. 1 The Archaeology of Error How Humans Get Stuck Discover how false beliefs take root and why some errors persist for centuries.
  2. 2 The Authority Cascade How Humans Get Stuck Understand how deference to authority propagates errors through institutions and cultures.
  3. 3 Survivorship Bias at Scale How Humans Get Stuck Learn why we systematically overlook failures and how this distorts our understanding of success.
  4. 4 The Sunk Cost of Consensus How Humans Get Stuck Explore how group consensus creates inertia that prevents correction of known errors.
  5. 5 The Einstellung Effect How Humans Get Stuck Understand how expertise can become a trap when familiar solutions block better alternatives.
  6. 6 Cognitive Load and Its Limits Metacognition Learn how cognitive load affects judgment and how to manage your mental resources.
  7. 7 Calibration: Knowing What You Know Metacognition Develop the critical skill of accurately judging your own knowledge and confidence.
  8. 8 Desirable Difficulties Metacognition Discover why the things that feel hardest often produce the deepest learning.
  9. 9 Red Flags for Bad Thinking How Humans Get Stuck Build a practical checklist for spotting unreliable claims and flawed reasoning.
  10. 10 How to Disagree Productively How Humans Get Stuck Learn frameworks for constructive disagreement that advance understanding rather than entrench positions.
  11. 11 Cognitive Biases in Everyday Life Applied Psychology Apply psychological research on cognitive biases to recognize and counteract them in daily decisions.
  12. 12 The Speed of Truth
  13. 13 The Outsider Problem
  14. 14 Crisis and Correction
  1. 1 The Quantum Revolution Quantum Mechanics Trace the historical experiments that shattered classical physics and launched the quantum era.
  2. 2 The Wave Function and Schrodinger Equation Quantum Mechanics Learn the central equation of quantum mechanics and the probabilistic meaning of the wave function.
  3. 3 Exactly Solvable Problems Quantum Mechanics Solve the particle in a box, step potential, and other fundamental quantum systems.
  4. 4 The Hydrogen Atom Quantum Mechanics Apply quantum mechanics to the hydrogen atom and understand atomic energy levels.
  5. 5 Linear Algebra and Dirac Notation Quantum Mechanics Master the mathematical language of quantum mechanics: Hilbert spaces, bras, and kets.
  6. 6 Spin Quantum Mechanics Discover the intrinsic angular momentum of particles and the Stern-Gerlach experiment.
  7. 7 Perturbation Theory Quantum Mechanics Learn approximation methods for solving quantum problems that lack exact solutions.
  8. 8 Entanglement and Bell's Theorem Quantum Mechanics Explore quantum entanglement, Bell inequalities, and what they reveal about the nature of reality.
  9. 9 Quantum Information Quantum Mechanics Discover how quantum mechanics enables quantum computing, teleportation, and cryptography.
  10. 10 Quantum Technologies Quantum Mechanics Survey cutting-edge quantum technologies from quantum sensors to quantum computers.
  11. 11 Time Evolution — Schrödinger vs. Heisenberg Pictures
  12. 12 Angular Momentum Algebra
  13. 13 Symmetry and Conservation Laws
  14. 14 Eigenvalue Problems and Spectral Theory