InterviewsVector
Original Academy

Legacy mirror · noindex · upstream phase 3

Deep Learning Core

Neural networks from first principles. No frameworks until you build one.

Provenance: this phase outline and its lesson readings are preserved from ai-engineering-from-scratch by Rohit Ghumare under the MIT License. InterviewsVector does not claim authorship. These archive pages remain available for old links and progress, but are excluded from indexing.

Attributed readings

  1. 01The Perceptron: Where It All StartedThe perceptron is the atom of neural networks. Split it open and you find weights, a bias, and a decision.
  2. 02Multi-Layer Networks & Forward PassOne neuron draws a line. Stack them, and you can draw anything.
  3. 03Backpropagation from ScratchBackpropagation is the algorithm that makes learning possible. Without it, neural networks are just expensive random number generators.
  4. 04Activation Functions: ReLU, Sigmoid, GELU & WhyWithout nonlinearity, your 100-layer network is a fancy matrix multiply. Activations are the gates that let neural networks think in curves.
  5. 05Loss Functions: MSE, Cross-Entropy, ContrastiveYour 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 t…
  6. 06Optimizers: SGD, Momentum, Adam, AdamWGradient 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.
  7. 07Regularization: Dropout, Weight Decay, BatchNormYour 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.
  8. 08Weight Initialization & Training StabilityInitialize wrong and training never starts. Initialize right and 50 layers train as smoothly as 3.
  9. 09Learning Rate Schedules & 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 el…
  10. 10Build 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 t…
  11. 11Introduction to PyTorchYou built the engine from pistons and crankshafts. Now learn the one everyone actually drives.
  12. 12Introduction to JAXPyTorch mutates tensors. TensorFlow builds graphs. JAX compiles pure functions. That last one changes how you think about deep learning.
  13. 13Debugging 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.