AI From ScratchStart phase
Phase 03/13 lessons/~15 hours
Deep Learning Core
Neural networks from first principles. No frameworks until you build one yourself.
0 / 13 complete0%
Lessons
01The PerceptronUp nextThe perceptron is the atom of neural networks. Split it open and you find weights, a bias, and a decision.Build/~60 minutes/Python02Multi-Layer Networks and Forward PassOne neuron draws a line. Stack them, and you can draw anything.Build/~90 minutes/Python03Backpropagation from ScratchBackpropagation is the algorithm that makes learning possible. Without it, neural networks are just expensive random number generators.Build/~120 minutes/Python04Activation FunctionsWithout nonlinearity, your 100-layer network is a fancy matrix multiply. Activations are the gates that let neural networks think in curves.Build/~75 minutes/Python05Loss 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.Build/~75 minutes/Python06OptimizersGradient 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.Build/~75 minutes/Python07RegularizationYour 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.Build/~75 minutes/Python08Weight Initialization and Training StabilityInitialize wrong and training never starts. Initialize right and 50 layers train as smoothly as 3.Build/~90 minutes/Python09Learning 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.Build/~90 minutes/Python10Build 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. Yo...Build/~120 minutes/Python11Introduction to PyTorchYou built the engine from pistons and crankshafts. Now learn the one everyone actually drives.Build/~75 minutes/Python12Introduction to JAXPyTorch mutates tensors. TensorFlow builds graphs. JAX compiles pure functions. That last one changes how you think about deep learning.Build/~90 minutes/Python13Debugging 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.Build/~90 minutes/Python, PyTorch