Vizuara Books
Deep Learning Fundamentals
Build a neural network from scratch in pure NumPy.
Master deep learning from the ground up by coding an entire neural network by hand — neurons, forward pass, backpropagation, optimizers, and regularization. Every equation is derived and every line is written in plain NumPy before you ever touch a framework.
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.
00Foundations3 capsules
Foundations — 3 chapters.
01What is deep learning, really?conceptfree12 min02The neuron: a tiny math machineintuition🔒15 min03NumPy and the dot product primercode🔒13 min01Neural Network Architecture3 capsules
Neural Network Architecture — 3 chapters.
04Coding neurons and layerscode🔒13 min05The beauty of NumPy and the dot productcode🔒14 min06Stacking multiple layers togethercode🔒12 min02The Forward Pass5 capsules
The Forward Pass — 5 chapters.
07Implementing the dense layer classcode🔒13 min08Broadcasting and array summationcode🔒14 min09Coding activation functionscode🔒14 min10One full forward pass (no loss yet)code🔒14 min11Coding the cross-entropy lossmath🔒12 min03Optimization and Calculus3 capsules
Optimization and Calculus — 3 chapters.
12Introduction to optimizationconcept🔒13 min13Partial derivatives and gradientsmath🔒13 min14The chain rule: backbone of neural networksmath🔒13 min04The Backward Pass (Backpropagation)9 capsules
The Backward Pass (Backpropagation) — 9 chapters.
15Backpropagation on a single neuronmath🔒15 min16Backpropagation through a layer of neuronsmath🔒13 min17The role of matrices in backpropagationmath🔒13 min18Input derivatives in backpropagationmath🔒14 min19Coding the backpropagation building blockscode🔒13 min20Backpropagation through ReLUcode🔒13 min21Backpropagation through cross-entropy lossmath🔒15 min22Combined softmax + cross-entropy backwardmath🔒14 min23Building the full backpropagation pipelinecode🔒13 min05The Full Training Loop1 capsules
The Full Training Loop — 1 chapter.
24The entire forward-backward pass in Pythonproject🔒15 min06Optimizers6 capsules
Optimizers — 6 chapters.
25Coding the gradient descent optimizercode🔒15 min26Learning rate decayconcept🔒14 min27Momentum in trainingintuition🔒13 min28Coding the AdaGrad optimizercode🔒11 min29Coding the RMSProp optimizercode🔒14 min30Coding the Adam optimizercode🔒16 min07Recap: A Network from Scratch1 capsules
Recap: A Network from Scratch — 1 chapter.
31Neural networks from scratch, end to endconcept🔒13 min08Regularization and Testing4 capsules
Regularization and Testing — 4 chapters.
32Testing, generalization, and overfittingconcept🔒13 min33K-fold cross validationconcept🔒13 min34L1 and L2 regularizationmath🔒13 min35Dropout layerscode🔒14 min09Hands-On Projects3 capsules
Hands-On Projects — 3 chapters.
36Regression project: California Housingproject🔒14 min37Classification project: Fashion-MNISTproject🔒12 min38What we built, and where to go nextconcept🔒12 minRatings & reviews
No ratings yet. Yours would be the first.