Deep Learning, One Layer at a Time

From a single perceptron to backpropagation, optimizers, regularisation and the shape of a training curve.

27 modules Free, no login Updated 1 August 2026

About this track

Deep learning is a small number of ideas repeated at scale. This track introduces them in the order they build: one weighted sum, then an activation, then a layer, then a loss, then the gradient that moves the weights, then everything people add to stop it going wrong.

Because each page animates a single step, you can see what a learning rate actually does to a descent path, why a training curve separates from the validation curve, and what dropout removes on each forward pass.

All 27 modules, in teaching order

  1. 01Perceptron ClassifierAdjust the weights and bias of a single perceptron by hand and watch its decision boundary swing across the data.
  2. 02Weights & BiasesSee what the numbers a network learns are actually for: weights scale each input, bias shifts where the neuron fires.
  3. 03Activation Functions in DLCompare ReLU, sigmoid, tanh and others on the same input, and see how each one bends the signal passing through a layer.
  4. 04Neural Network VisualizerBuild a neural network layer by layer and watch data flow forward through weights, biases and activations into a prediction.
  5. 05How Loss is CalculatedFollow a prediction through to a single loss value, and see how the error signal that drives all learning is actually computed.
  6. 06Gradient DescentWatch gradient descent step downhill across a loss surface, and see how the learning rate decides between converging and diverging.
  7. 07Linear Regression with Gradient DescentTake gradient descent one step at a time and watch the best-fit line and its mean squared error converge together.
  8. 08Optimizers in Neural NetworksRun several optimizers in parallel on one loss surface and see how momentum and adaptive learning rates change the route.
  9. 09Optimizers in 3DRace SGD, Momentum, RMSprop and Adam across a 3D loss landscape and watch which of them escape local minima and which get stuck.
  10. 10Learning Rate SchedulingCompare a fixed learning rate against a decaying schedule, and watch scheduling rescue a model that would otherwise overshoot.
  11. 11Batch Processing in NetworksCompare stochastic, mini-batch and full-batch training, and see how batch size trades gradient noise against speed.
  12. 12Gradient Descent Batch ProcessingChange one control at a time and watch how batch size reshapes the path gradient descent takes toward the minimum.
  13. 13Feature Scaling & Weight BiasSee what happens when one feature is measured in thousands and another in decimals, and how scaling rebalances the gradients.
  14. 14Weight Initialization MethodsCompare He, Xavier, random and zero initialisation, and watch poor starting weights kill a deep network before it learns.
  15. 15Vanishing & Exploding GradientsWatch gradients shrink to nothing or blow up as they multiply back through layers, and see what keeps them in range.
  16. 16Batch Normalization in Deep NetworksToggle batch normalisation on a deep network and watch it rescale layer outputs to keep gradients stable as they flow back.
  17. 17Overfitting vs UnderfittingMove model complexity from too simple to too flexible and watch the gap open between training and validation performance.
  18. 18Model Training CurvesRead training and validation curves like a practitioner: spot underfitting, a healthy fit and overfitting from their shape alone.
  19. 19Dropout RegularizationSwitch neurons off at random during training and watch dropout stop the network leaning on any single pathway.
  20. 20Regularization TechniquesCompare L1 and L2 penalties, and watch Lasso zero out useless weights while Ridge shrinks all of them smoothly.
  21. 21Early StoppingWatch validation loss bottom out then start climbing, and see early stopping halt training at the moment generalisation peaks.
  22. 22Hyperparameter TuningRun grid search and random search side by side on the same model and see which finds strong hyperparameters in fewer trials.
  23. 23Data SparsityFeed mostly-zero inputs through a network and watch entire pathways go dormant, because anything multiplied by zero stays zero.
  24. 24Neural Network for RegressionAdapt a neural network to predict continuous values, and see how its output layer and loss differ from a classifier's.
  25. 25Neural Network for Unsupervised LearningTrain a network with no labels at all and watch it uncover structure by learning to reconstruct its own input.
  26. 26Model ReproducibilityFix the random seed and see exactly what becomes repeatable: initial weights and the order training data is shuffled in.
  27. 27Model Training on CPU vs GPUInteractive visualization of CPU vs GPU in deep learning. Learn how batch size and parallelism affect training speed on VizLearn.

Other tracks