Vizuara Books
Neural Networks from Scratch
Build a working neural network from an empty file.
From matrix multiplication to a trained classifier: softmax, cross-entropy, the forward and backward pass, and optimizers, all coded by hand in NumPy. No autograd, no framework magic — just the math, made visible and built up one layer at a time.
Read on your Kindle
We'll send this whole book straight to your Kindle — it opens natively, so you can resize the text, read fully offline, and it remembers where you left off. Nothing to download or manage.
Sending to Kindle is for subscribers — subscribe to read the whole library on your Kindle.
00The Ten Questions4 capsules
The Ten Questions — 4 chapters.
01Introduction and the Ten Questionsintuition16 min02What a Neural Network Must Actually Doconcept13 min03A Mathematical Function to Switch a Neuron On or Offmath16 min04Matrix Multiplication as a Classifiermath13 min01Turning Scores into Probabilities3 capsules
Turning Scores into Probabilities — 3 chapters.
05From Raw Scores to a Probability Distributionintuition13 min06The Softmax Functionmath14 min07Tensors: The Data Containersconcept13 min02Weights and Wiring4 capsules
Weights and Wiring — 4 chapters.
08The Logic for Calculating Weight Valuesmath13 min09Setting Up the Neural Networkcode13 min10Activation Functionsconcept13 min11The Network as One Big Functionintuition13 min03How a Network Learns6 capsules
How a Network Learns — 6 chapters.
12Teaching, or Training, a Neural Networkintuition13 min13The Forward Pass and Cross-Entropy Lossmath14 min14The Backward Pass: The Intuitionintuition14 min15The Backward Pass: Gradients by Handmath15 min16Weight Updation with Gradient Descentmath15 min17Hyperparameter Tuningconcept17 min04Context and Review3 capsules
Context and Review — 3 chapters.
18A Glimpse of Convolutional Neural Networksconcept14 min19Relooking at the Ten Questionsintuition12 min20Masterclass: Building the Whole Thing in Codeintuition12 min05Coding the Layers7 capsules
Coding the Layers — 7 chapters.
21The Problem: A Spiral Datasetproject13 min22Designing the Dense Layer Classcode13 min23Coding the Layer Forward Passcode13 min24Coding the Layer Backward Passcode11 min25Adding Activation Functionscode13 min26ReLU: Forward and Backward Passcode14 min27Softmax: The Forward Pass in Codecode13 min06Loss, Optimizer, and Training6 capsules
Loss, Optimizer, and Training — 6 chapters.
28Cross-Entropy Loss: The Forward Passcode13 min29The Combined Softmax + Loss Backward Passmath14 min30Optimizers: Beyond Plain Gradient Descentconcept14 min31Coding the Optimizercode11 min32Training the Entire Networkproject14 min33Visualizing the Resultsproject13 minRatings & reviews
No ratings yet. Yours would be the first.