YOUR FOUNDATION-FIRST SYLLABUS
Speech & audio
Start with sound stored as numbers. Follow a system that turns speech into text and text back into speech, then check the words, sound, and timing.
0 of 61 core ideas demonstrated60 lessons780 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 8–13 How computers represent a problem Explore everyday AI ideas; how AI got here; how computers represent a problem. 6 lessons · 0 of 6 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 exploreChapter 3 · Lessons 14–20 Inside a neural network: Inside an artificial neuron Explore learning from sequences and sound; learning from useful data; learning to predict; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
14
The numbers you actually need Math preparation · 10 min
To explore15 A function is a rule Math preparation · 9 min
To explore16 From a waveform to time-frequency features Learning mechanisms · 14 min
To explore17 From the world to a dataset Learning mechanisms · 11 min
To explore18 Build a tiny prediction model Learning mechanisms · 11 min
To explore19 Inside an artificial neuron Learning mechanisms · 14 min
To explore20 Why layers need more than multiplication Learning mechanisms · 12 min
To exploreChapter 4 · Lessons 21–26 Inside a neural network: Trace inputs through layers to a loss Explore inside a neural network; helping a model improve; math preparation when it is needed. 6 lessons · 0 of 7 core ideas demonstrated
21
Vectors: lists that work together Math preparation · 10 min
To explore22 Read an equation one symbol at a time Math preparation · 10 min
To explore23 Follow shapes through a numerical layer Math preparation · 10 min
To explore24 Trace inputs through layers to a loss Learning mechanisms · 17 min
To explore25 How does a model improve a prediction? Learning mechanisms · 32 min
To explore26 A derivative is a local change Math preparation · 13 min
To exploreChapter 5 · Lessons 27–32 Inside a neural network: How an error reaches earlier weights Explore inside a neural network; learning from sequences and sound; turning language into model inputs; and supporting ideas. 6 lessons · 0 of 6 core ideas demonstrated
27
The chain rule, one step at a time Math preparation · 13 min
To explore28 How an error reaches earlier weights Learning mechanisms · 11 min
To explore29 Let the graph carry derivatives Learning mechanisms · 12 min
To explore30 Carry a state from one step to the next Learning mechanisms · 14 min
To explore31 How text becomes tokens Learning mechanisms · 13 min
To explore32 From token IDs to learned vectors Learning mechanisms · 14 min
To exploreChapter 6 · Lessons 33–39 Learning from sequences and sound Explore turning language into model inputs; learning from sequences and sound; math preparation when it is needed. 7 lessons · 0 of 7 core ideas demonstrated
33
Probability without the mystery Math preparation · 10 min
To explore34 Powers and logarithms, one step at a time Math preparation · 11 min
To explore35 How a language model takes its next step Your system, connected · 15 min
To explore36 Map one sequence into another Learning mechanisms · 17 min
To explore37 Map sound into words with an alignment model Learning mechanisms · 14 min
To explore38 Generate sound from a representation Learning mechanisms · 14 min
To explore39 Averages over uncertain outcomes Math preparation · 9 min
To exploreChapter 7 · Lessons 40–46 Learning from useful data Explore learning from useful data; learning from sequences and sound; math preparation when it is needed. 7 lessons · 0 of 7 core ideas demonstrated
40
What can a small experiment tell us? Math preparation · 10 min
To explore41 Clean data without erasing the problem Learning mechanisms · 12 min
To explore42 Protect the examples used to judge a model Learning mechanisms · 15 min
To explore43 Who is represented by the data? Learning mechanisms · 14 min
To explore44 Decide what success means before training Learning mechanisms · 12 min
To explore45 Predict the future without borrowing information from it Learning mechanisms · 14 min
To explore46 Judge quality across time, languages, and delay Learning mechanisms · 14 min
To exploreChapter 8 · Lessons 47–53 Learning to predict Explore learning to predict; working with uncertainty; math preparation when it is needed. 7 lessons · 0 of 7 core ideas demonstrated
47
Turn a linear score into a class probability Learning mechanisms · 11 min
To explore48 Look inside the average score Learning mechanisms · 14 min
To explore49 Probability, likelihood, and what is unknown Learning mechanisms · 11 min
To explore50 Update a belief using new evidence Learning mechanisms · 13 min
To explore51 Value a choice and its later consequences Math preparation · 12 min
To explore52 Turn a probability into a justified action Learning mechanisms · 11 min
To explore53 Control complexity without peeking at the answer Learning mechanisms · 12 min
To exploreChapter 9 · Lessons 54–60 Testing what a model has learned Explore testing what a model has learned; how computers represent a problem; checking reliability and behavior; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
54
Evaluate the procedure that chose the model Learning mechanisms · 14 min
To explore55 Change one thing and measure what follows Learning mechanisms · 13 min
To explore56 Repeat an experiment without confusing luck with truth Learning mechanisms · 11 min
To explore57 Make the result possible to inspect Learning mechanisms · 12 min
To explore58 Measure the behavior that the task actually needs Learning mechanisms · 14 min
To explore59 Decide whose problem the system solves and who bears its errors Learning mechanisms · 12 min
To explore60 Project: trace a speech and audio system Your system, connected · 35 min
To exploreOptional extensions and comparisons (7)
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.Misuse in practice: jailbreaks, deepfakes, and provenanceA familiar face or voice is no longer proof of who is speaking. Learn how misuse works and the checks that still hold.Turn images, sound, and video into manageable model inputsTurn sound into discrete tokens a model can generate, one step at a time.Train alignment, generation, and instruction behavior across modalitiesHow text-to-image and text-to-audio systems are trained stage by stage.Compare language, image, audio, and state-space artifactsCompare Whisper, EnCodec, CLIP, and diffusion models side by side: what each takes in and produces.Choose what to keep, add, and revealLSTMs and GRUs, the sequence models that powered speech recognition before transformers.