🤖 Deep Learning with Neural Networks and TensorFlow

What Deep Learning Really Is (And When It Beats Classic Machine Learning)

14 min

Activation Functions: How Networks Learn to Bend

14 min

Forward and Backpropagation: Guess First, Then Learn From the Mistake

12 min

Loss Functions and Optimizers: Measuring "How Wrong" and Getting Less Wrong

18 min

Loss Functions and Optimizers: Measuring "How Wrong" and Getting Less Wrong

19 min

Regularization: So Models Learn Instead of Memorize

14 min

Regularization: So Models Learn Instead of Memorize

14 min

Your First Model With the Keras Sequential API

12 min

Compiling a Model: Loss, Optimizer, Metrics

19 min

Training, Validation, and Reading the Learning Curves

15 min

The Functional API: For Models That Branch and Merge

15 min

Saving, Loading, and Using Callbacks

19 min

Why PyTorch Feels Different From Keras

15 min

Tensors, Autograd, and the Computation Graph

14 min

Building a Model With nn.Module

17 min

Writing Your Own Training Loop (And Understanding Every Line)

19 min

Datasets, DataLoaders, and Batching

14 min

Saving Models and Moving Work Onto the GPU

18 min

The Big Idea: Don't Start From Scratch

13 min

Pretrained Models and Where to Find Them

12 min

Feature Extraction vs Fine-Tuning

15 min

Transfer Learning in Keras, Step by Step

17 min

Transfer Learning in PyTorch, Step by Step

18 min

Common Mistakes and How to Dodge Them

13 min

Computer Vision: Teaching Machines to See

16 min

NLP: Teaching Machines to Read

18 min

Time Series: Teaching Machines to Predict What Comes Next

19 min

When Deep Learning Is the Right Tool for the Job

18 min

When Deep Learning Is Overkill, and What to Use Instead

14 min

Where to Go Next: Your Roadmap After This Course

16 min