Introduction Into to deep learning Intelligence: The ability to process information and use it for future …
Deep Learning Fundamentals
Build a solid foundation in neural networks from first principles. Covers the forward pass, activation functions, loss functions, backpropagation, and the full training loop — with visual explanations.
- 1Learning from Introduction to Deep Learning
- 2Backpropagation Explained Visually: How Neural Networks Actually Learn
A practical visual guide to backpropagation, computation graphs, the chain rule, and how gradients flow backward through a neural network.
- 3Forward Pass Explained: From a Single Neuron to Matrix Form
A step-by-step guide to the forward pass in neural networks, starting with one neuron and scaling to dense layers and matrix multiplication.
- 4Multi-Layer Perceptron Explained: Dense Networks from First Principles
A practical guide to multi-layer perceptrons, dense layers, width vs depth, weight matrices, and when fully connected networks are still the right tool.
- 5MSE vs Cross-Entropy: Which Loss Function Should You Use?
A practical guide to mean squared error and cross-entropy loss, including regression vs classification, intuition, formulas, and when each one is the right choice.
- 6Training Loop Explained: Batches, Epochs, Iterations, and Convergence
A practical guide to the neural network training loop, including forward pass, loss, backward pass, optimizer steps, mini-batches, epochs, and how to reason about convergence.