Deep Learning Core
Neural networks from first principles. No frameworks until you build one yourself.
13 lessons · 13 visual stories
0/13 complete · 0%
#LessonTypeLanguagesTimeOpen
01The PerceptronThe perceptron is the atom of neural networks. Split it open and you find weights, a bias, and a decision.BuildPython45 min▸ Visual story02Multi-Layer Networks and Forward PassOne neuron draws a line. Stack them, and you can draw anything.BuildPython75 min▸ Visual story03Backpropagation from ScratchBackpropagation is the algorithm that makes learning possible. Without it, neural networks are just expensive random number generators.BuildPython75 min▸ Visual story04Activation FunctionsWithout nonlinearity, your 100-layer network is a fancy matrix multiply. Activations are the gates that let neural networks think in curves.BuildPython45 min▸ Visual story05Loss FunctionsYour network makes a prediction. The ground truth says otherwise. How wrong is it? That number is the loss. Pick the wrong loss function and your model optimizes for the wrong thing entirely.BuildPython45 min▸ Visual story06OptimizersGradient descent tells you which direction to move. It says nothing about how far or how fast. SGD is a compass. Adam is GPS with traffic data.BuildPython75 min▸ Visual story07RegularizationYour model gets 99% on training data and 60% on test data. It memorized instead of learning. Regularization is the tax you impose on complexity to force generalization.BuildPython75 min▸ Visual story08Weight Initialization and Training StabilityInitialize wrong and training never starts. Initialize right and 50 layers train as smoothly as 3.BuildPython45 min▸ Visual story09Learning Rate Schedules and WarmupThe learning rate is the single most important hyperparameter. Not the architecture. Not the dataset size. Not the activation function. The learning rate. If you tune nothing else, tune this.BuildPython45 min▸ Visual story10Build Your Own Mini FrameworkYou have built neurons, layers, networks, backprop, activations, loss functions, optimizers, regularization, initialization, and LR schedules. All as separate pieces. Now wire them together into a framework. Not PyTorch. Not TensorFlow. Yours.BuildPython120 min▸ Visual story11Introduction to PyTorchYou built the engine from pistons and crankshafts. Now learn the one everyone actually drives.BuildPython75 min▸ Visual story12Introduction to JAXPyTorch mutates tensors. TensorFlow builds graphs. JAX compiles pure functions. That last one changes how you think about deep learning.BuildPython75 min▸ Visual story13Debugging Neural NetworksYour network compiled. It ran. It produced a number. The number is wrong and nothing crashed. Welcome to the hardest kind of debugging -- the kind where there is no error message.BuildPython, PyTorch75 min▸ Visual story