YOUR FOUNDATION-FIRST SYLLABUS
Scientific AI
Explore how AI helps ask scientific questions, represent molecules or physical processes, and choose experiments. Compare several approaches and learn why a plausible prediction still needs scientific evidence.
0 of 66 core ideas demonstrated65 lessons800 estimated minutes remaining
Already know some of this?
Go straight to an idea’s knowledge check. Passing its different checks without hints carries that evidence into this path. Checking an advanced idea does not award its prerequisites; you can still explore them.
Check what I already knowTHE IDEAS, IN ORDER
Shared credit is automaticBuild your understanding.
Chapter counts use compatible knowledge-check evidence. Reading a lesson does not mark its ideas as demonstrated.
Chapter 1 · Lessons 1–7 Meet an AI system Start with an everyday task, then follow its inputs, model, and output. 7 lessons · 0 of 7 core ideas demonstrated Up next
01
What is AI? Start with an everyday task Common Ground · 11 min
To explore02 Inputs and outputs: what goes in and what comes out Common Ground · 13 min
To explore03 Data and examples: what a computer can learn from Common Ground · 10 min
To explore04 What is a model? A small rule inside a bigger app Common Ground · 10 min
To explore05 Weights: the adjustable numbers in a model Common Ground · 12 min
To explore06 Training and inference: changing a rule or using it Common Ground · 13 min
To explore07 Follow one small AI system from start to finish Common Ground · 9 min
To exploreChapter 2 · Lessons 8–14 How computers represent a problem Explore everyday AI ideas; how AI got here; how computers represent a problem; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
08
Different ways to solve the same problem Common Ground · 11 min
To explore09 How to tell whether an AI answer is useful Common Ground · 10 min
To explore10 The questions that shaped AI Common Ground · 15 min
To explore11 How a computer stores a picture or a sentence Learning mechanisms · 16 min
To explore12 Describe a computation so someone else can follow it Learning mechanisms · 11 min
To explore13 What a representation makes easy to learn Learning mechanisms · 12 min
To explore14 The numbers you actually need Math preparation · 10 min
To exploreChapter 3 · Lessons 15–21 Reasoning with facts and rules Explore reasoning with facts and rules; learning from useful data; learning to predict; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
15
Sets, graphs, and counting possibilities Math preparation · 10 min
To explore16 Reason with statements that are true or false Learning mechanisms · 13 min
To explore17 Talk about objects and relationships Learning mechanisms · 12 min
To explore18 Store relationships so they can be queried Learning mechanisms · 11 min
To explore19 From the world to a dataset Learning mechanisms · 11 min
To explore20 A function is a rule Math preparation · 9 min
To explore21 Build a tiny prediction model Learning mechanisms · 11 min
To exploreChapter 4 · Lessons 22–28 Inside a neural network: Inside an artificial neuron Explore inside a neural network; using AI to investigate science; math preparation when it is needed. 7 lessons · 0 of 7 core ideas demonstrated
22
Inside an artificial neuron Learning mechanisms · 14 min
To explore23 Why layers need more than multiplication Learning mechanisms · 12 min
To explore24 Vectors: lists that work together Math preparation · 10 min
To explore25 Read an equation one symbol at a time Math preparation · 10 min
To explore26 Follow shapes through a numerical layer Math preparation · 10 min
To explore27 Trace inputs through layers to a loss Learning mechanisms · 17 min
To explore28 Learn by exchanging messages across a graph Learning mechanisms · 14 min
To exploreChapter 5 · Lessons 29–35 Inside a neural network: How an error reaches earlier weights Explore using AI to investigate science; helping a model improve; inside a neural network; and supporting ideas. 7 lessons · 0 of 8 core ideas demonstrated
29
Distances, neighborhoods, and transformations Math preparation · 12 min
To explore30 Build symmetry into predictions about geometry Learning mechanisms · 14 min
To explore31 How does a model improve a prediction? Learning mechanisms · 32 min
To explore32 A derivative is a local change Math preparation · 13 min
To explore33 The chain rule, one step at a time Math preparation · 13 min
To explore34 How an error reaches earlier weights Learning mechanisms · 11 min
To explore35 Let the graph carry derivatives Learning mechanisms · 12 min
To exploreChapter 6 · Lessons 36–43 Learning from useful data Explore using AI to investigate science; learning to predict; learning from useful data; and supporting ideas. 8 lessons · 0 of 8 core ideas demonstrated
36
Follow a changing state through time Math preparation · 12 min
To explore37 Learn functions while using equations or families of solutions Learning mechanisms · 14 min
To explore38 Probability without the mystery Math preparation · 10 min
To explore39 Powers and logarithms, one step at a time Math preparation · 11 min
To explore40 Turn a linear score into a class probability Learning mechanisms · 11 min
To explore41 Averages over uncertain outcomes Math preparation · 9 min
To explore42 Who is represented by the data? Learning mechanisms · 14 min
To explore43 Decide what success means before training Learning mechanisms · 12 min
To exploreChapter 7 · Lessons 44–51 Working with uncertainty Explore learning to predict; working with uncertainty; learning from useful data; and supporting ideas. 8 lessons · 0 of 8 core ideas demonstrated
44
Look inside the average score Learning mechanisms · 14 min
To explore45 Probability, likelihood, and what is unknown Learning mechanisms · 11 min
To explore46 Update a belief using new evidence Learning mechanisms · 13 min
To explore47 Value a choice and its later consequences Math preparation · 12 min
To explore48 Turn a probability into a justified action Learning mechanisms · 11 min
To explore49 What can a small experiment tell us? Math preparation · 10 min
To explore50 Clean data without erasing the problem Learning mechanisms · 12 min
To explore51 Protect the examples used to judge a model Learning mechanisms · 15 min
To exploreChapter 8 · Lessons 52–58 Testing what a model has learned Explore learning to predict; testing what a model has learned; how computers represent a problem; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
52
Control complexity without peeking at the answer Learning mechanisms · 12 min
To explore53 Evaluate the procedure that chose the model Learning mechanisms · 14 min
To explore54 Change one thing and measure what follows Learning mechanisms · 13 min
To explore55 Repeat an experiment without confusing luck with truth Learning mechanisms · 11 min
To explore56 Make the result possible to inspect Learning mechanisms · 12 min
To explore57 Measure the behavior that the task actually needs Learning mechanisms · 14 min
To explore58 Build a test whose score supports the intended claim Learning mechanisms · 12 min
To exploreChapter 9 · Lessons 59–65 Using AI to investigate science Explore using AI to investigate science; understanding causes and change; working with uncertainty; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
59
Evaluate scientific predictions beyond familiar benchmarks Learning mechanisms · 13 min
To explore60 Ask what would change if an action changed the world Learning mechanisms · 15 min
To explore61 Factor a joint distribution into smaller pieces Learning mechanisms · 11 min
To explore62 Measure surprise and compare distributions Math preparation · 12 min
To explore63 Learn distributions over plausible explanations Learning mechanisms · 11 min
To explore64 Choose expensive experiments using a surrogate model Learning mechanisms · 13 min
To explore65 Use models to propose experiments and test hypotheses Learning mechanisms · 14 min
To exploreOptional extensions and comparisons (5)
These lessons deepen or compare the reference design. They do not add requirements to this path’s completion.
How to use this school without getting lostOptional orientation: how paths, side lessons, and practice fit together, plus study habits that make learning stick.Practice, progress, and knowing what you understandOptional orientation: use practice, mistakes, and spaced review to find out what you really understand.Learn a vector field and let a solver define continuous depthNeural networks as continuous dynamics, a natural fit for scientific time series.Evaluate new computing and learning claims without assuming a breakthroughQuantum ML and other new ideas: how to judge a breakthrough claim before believing it.Maintain a research record that can change with evidenceKeep up with fast-moving research without being fooled by headlines.