Overview
Syllabus
Video overview
Why use neural networks
How neural nets work architecture basics
Hyperparameter overview batch size, optimizer, dropout, learning rate, epochs
How do we choose layers, neurons, & other parameters?
Why do we need an activation function?
What activation function should I use?
Keras vs Tensorflow vs PyTorch
Coding starts github & setup
Writing our first neural network linear example
Selecting optimizer & loss function model.compile
Fitting training data to our model model.fit
Shuffle order of training data
Evaluate model on test data model.evaluate
Example #2: Classifying quadratic data
Example #3: Classifying 6 clusters of data try on your own
Using network to predict a single data point model.predict
Example #4: Classifying multiple labels at a time BinaryCrossentropy loss
Example #5: Classifying our complex data from start of video
Conclusion & Next steps of learning neural nets
Taught by
Keith Galli