Make it stick.
Close the explanation, retrieve the idea, then test it in a different setting.
Start with lessons you saved for review. If you have none, revisit a completed lesson, or try one of the foundational lessons below. Review mode starts the checks fresh without removing earlier completion or notes.
Your saved lessons appear here when local progress is available.
- What is a signal?
- Frequency, amplitude and phase
- Vectors and similarity
- Complex numbers and rotation
- Slopes and gradients
- Probability and uncertainty
- Noise and signal-to-noise ratio
- Data splits and leakage
- Sampling and time
- Aliasing and Nyquist
- Quantisation and clipping
- Resampling safely
- Projection onto waves
- The discrete Fourier transform
- Windows and leakage
- Time-frequency analysis
- Linearity and time invariance
- Convolution step by step
- Frequency response and filter trade-offs
- Recurrence and stability
- Features and linear regression
- Gradient descent
- Classification and cross-entropy
- Evaluation and generalisation
- Nonlinear features and neural networks
- The chain rule and backpropagation
- Convolutions in neural networks
- Regularisation and model selection
- Position and representation
- Attention as weighted retrieval
- Rotary position
- State-space memory
- Nonlinear aliasing
- FFTs and memory traffic
- Numerical stability
- Benchmarking and reproducibility
- Project: a denoising pipeline
- Project: a leakage-safe classifier
- Project: a sequence-model investigation
- Project: read and reproduce a research claim
A small retrieval routine
- Explain the core idea without reading it first.
- Answer the checks, then inspect any feedback.
- Change an example or assumption and predict the result.
- Record what you corrected and when you want to revisit it.
This is a manual review aid, not an automated spaced-repetition schedule or a measured claim about this course’s learning outcomes.