All courses
Online · Self-paced · IXILab
Human-AI Interaction and Collaboration
A virtual online course on how people and computers work together, played as short browser games. Walk a map, meet trainers, try live demos, and pass each leader’s quiz.
Course info
- Format
- Browser games, one per chapter. Nothing to install.
- Length
- 20–45 minutes per chapter
- Author
- Dr. Yi-Chi Liao (yichi@csie.ntu.edu.tw)
- Based on
- The NTU course Human-AI Interaction & Collaboration (CSIE 5648)
- Language
- English
- Audience
- Anyone. No prior knowledge of HCI is assumed.
- Cost
- Free
How to play
Start at Chapter 01!
Walk with the arrow keys or WASD, talk with Space or Enter, and answer with 1–4. On a phone, use the on-screen pad. Your progress is saved in your browser.
Objectives
After the course, you should be able to…
- Define Human-Computer Interaction (HCI).
- Name the key elements in the model of human-computer interaction, from sensing input to how people perceive, decide and learn.
- Name the key phases of the design process.
- Run a short design sprint, from a design brief to testing a paper prototype.
- Define research, evaluation and controlled experiments in HCI.
- Plan and run a controlled experiment to evaluate a working system, and analyze it with ANOVA.
- Know different research methods, and when to use them.
- Explain how a neural network maps input to output, and how it learns with gradient descent and backpropagation.
- Explain how language becomes tokens and embeddings, how attention with queries, keys and values builds context, and how self-supervised learning trains large language models.
- Harness AI models without updating them, through prompt engineering, context engineering, inference-time strategies, and prompt evaluation.
Chapters
Five parts, twenty-two chapters, three areas each.
Every trainer teaches one idea with a live demo, and each area ends with a leader’s quiz. Select a chapter to play it. More parts will be added.
Part 1 · Introduction to Human-Computer Interaction
Chapter 01
~30 min
~30 min
Introduction to HCI
- Origin Road What HCI is, its three roots, the human-computer loop, and the information flow of a mouse
- Sensor Woods Transducers and transfer functions, calibration, noise and filtering, the 1€ filter, recognizers
- Mind Lake The Human Processor Model, computational rationality, and reinforcement learning
Chapter 02
~25 min
~25 min
Design workflows
- Problem Plains Problem space and solution space, the value of a problem–solution pair, who decides what is valuable, user research, competitive analysis and personas
- Prototype Pass Brainstorming, and low-, mid- and high-fidelity prototypes
- Workflow Harbor Waterfall vs. iterative design, design with limited time, and how product teams work before and after AI
Chapter 03
~25 min
~25 min
Hands-on design sprint
- Brief Field Reading a design brief, writing good interview questions, and interviewing a user
- Sketch Pass Writing a problem statement, rough sketches, choosing one, and not assuming you know the problem or the solution
- Test Harbor Paper prototypes, testing without helping, iterating and reflecting
Part 2 · Research methods and evaluation
Chapter 04
~20 min
~20 min
Research and evaluation
- Question Meadow The questions a design process raises, and what “better” means in a redesign
- Definition Grove Research, evaluation and controlled experiments, and how they nest
- Method Bay Four research methods, and picking one for each question
Chapter 05
~30 min
~30 min
Controlled experiments
- Hypothesis Road Hypotheses, independent and dependent variables, and why controlled experiments show cause and effect
- Variable Woods Nominal, ordinal, interval and ratio data, testable research questions, and controlled and confounding variables
- Latin Lake Within- vs. between-subject designs, counterbalancing, balanced Latin squares, and planning a full experiment
Chapter 06
~30 min
~30 min
Statistical analysis
- Null Hollow Is the difference real? The null hypothesis, and data as distributions
- Spread Springs Mean and median, variance and n − 1, standard deviation, and why ANOVA compares spreads
- Report Reef Running and reporting an ANOVA (df, F, p), and a typing experiment you take part in
Chapter 07
~20 min
~20 min
Other research methods
- Question Crossing Qualitative methods: words vs. numbers, and the questions they answer
- Voice Valley Interviews, think-aloud protocols, and focus groups
- Field Shore Field studies, mixed methods, and choosing a method for a question
Part 3 · Deep learning
Chapter 08
~30 min
~30 min
Neural networks
- Pixel Path AI, ML and deep learning, a network as a function, and the input layer as 784 pixel activations
- Feature Forest Hidden and output layers, learned features, weights and the weighted sum, and a line detector
- Sigmoid Shore The sigmoid activation, the bias, and the matrix form σ(Wx + b)
Chapter 09
~30 min
~30 min
Gradient descent
- Label Lane How many parameters a network has, training data and labels, and accuracy during training
- Cost Canyon The cost function, learning as minimizing it, and why we step against the gradient
- Gradient Slope Gradient descent with a learning rate, reading the gradient vector, and what a trained network really learns
Chapter 10
~20 min
~20 min
The idea of backpropagation
- Nudge Meadow What backpropagation computes, and three ways to raise an output: bias, weights, or the previous layer
- Wishing Wells Which weights to raise most, which way each activation should move, and summing every output’s wishes
- Backflow River Wishes flowing back layer by layer, and full vs. stochastic (minibatch) gradient descent
Chapter 11
~30 min
~30 min
Backpropagation in math
- Sensitivity Steps The cost of one example, what depends on what, and how sensitive the cost is to a weight
- Chain Link Bridge The chain rule, the derivatives for the bias and the previous activation, and passing them back a layer
- Index Cliffs Many neurons (indices j, k), averaging over examples, the gradient vector, and the update w ← w − η∇C
Chapter 12
~40 min
~40 min
Computer vision models
- Keypoint Knoll Images as numbers, classic feature extraction and matching, and how CNNs and deep learning took over
- Kernel Creek Fully connected vs. convolutional layers, a CNN layer by layer, and image classification
- Bounding Box Bay Object detection (R-CNN, YOLO), hand-designed vs. learned features, and the family from CNNs to foundation models
Part 4 · Modern AI models
Chapter 13
~25 min
~25 min
Large language models
- Prompt Path What GPT stands for, next-token prediction, and how a chat is one growing text
- Corpus Canyon The scale of training data and compute, and the three steps from pretraining to harnessing
- Gap Gorge Next-token training pairs, and what GPT-3 does differently from earlier deep learning
Chapter 14
~25 min
~25 min
Embeddings
- One-Hot Hill Turning words into numbers: single numbers, one-hot vectors, and feature vectors that capture similarity
- Token Thicket Learning vectors from context, and what to embed: words, characters, or subword tokens
- Matrix Marsh Token IDs, the embedding matrix, and vector arithmetic like Paris − France + Italy ≈ Rome
Chapter 15
~25 min
~25 min
Attention
- Twin Bank Ford Why one word needs different meanings in different contexts: tokens, context, and contextualized embeddings
- Mixing Meadow Building meaning from context: “female king”, “Lego Eiffel tower”, and which words help
- Spotlight Ridge Attention weights, a weighted sum of context, and representations across layers
Chapter 16
~25 min
~25 min
Query, key and value
- Query Cove Which tokens are relevant: queries, keys, dot products and softmax
- Value Ridge Values, a full attention calculator, and where Q, K and V come from
- Root Lake The attention formula softmax(QKT / √dk) V, why we scale by √dk, and stacking layers
Chapter 17
~25 min
~25 min
Self-supervised learning and foundation models
- Nobody’s Orchard Where the training data come from: supervised vs. self-supervised learning
- Foundation Quarry Transformers at scale, foundation models vs. one model per task, and handling a new task
- Horizon Ridge Beyond text-only LLMs (multimodal models), and how GPT-3 learns without labels and writes one token at a time
Part 5 · Harnessing AI models
Chapter 18
~45 min
~45 min
From models to applications
- Ticket Terrace The gap between a model and an application, and five ways to make a model do what we want
- Misfire Marsh Harness failures: unclear instructions, missing or conflicting context, unusable output, and their fixes
- Token Budget Bluff The context window, budgeting its tokens, and why more context is not always better
Chapter 19
~45 min
~45 min
Prompt engineering
- Instruction Inlet Prompts vs. instructions, why prompting works, and where prompts come from
- Hierarchy Heights The prompt hierarchy, prompt injection (with the 2025 hidden-text case), and when system prompts fail
- Template Terrace Structured prompts, their typical sections, and prompt templates
Chapter 20
~45 min
~45 min
Context engineering
- Window Wharf When a prompt is not enough, choosing which context goes in, and the context budget
- Digest Dunes Compressing context: extractive and abstractive summaries, and LLMLingua
- Retrieval Reach In-context learning with examples, what GPT-3 found about few-shot learning, and retrieval-augmented generation (RAG)
Chapter 21
~25 min
~25 min
Inference-time strategies
- Checkpoint Hill Inference-time strategies, and generating hypotheses then verifying them
- Thought Trail Chain of thought (few-shot and zero-shot), when it helps, and self-consistency voting
- Schema Sound Structured outputs: JSON schemas, validation, and constrained decoding
Chapter 22
~25 min
~25 min
Prompt evaluation and optimization
- Test Set Terrace Which prompt is better? Building a test set with expected outputs, and measuring accuracy
- Judges’ Lagoon Prompt optimization, judging outputs when there is no metric, and the optimization loop
- Rewrite Rise Textual gradients: learning from the difference between a better and a worse prompt