Deep Learning Fundamentals - Classic Edition

Learn the relationship between machine learning and deep learning

Understand artificial neural networks and all their components

Gain an intuitive understanding of neural network training

Learn how neural networks are implemented in code

Understand fundamental network training concepts like learning rates and loss functions

Learn about potential problems that can arise during training and potential solutions

Gain an understanding of how to process data for neural networks

Learn about the different categories of datasets in deep learning: training, validation, test

Understand the different categories of learning: supervised, unsupervised, semi-supervised

Gain an understanding of all the components in a convolutional neural network (CNN)

Understand how CNNs detect patterns in image data

Learn how data is affected by zero padding and max pooling included in neural networks

Learn the mathematics behind backpropagation and how it's used during training

Gain an understanding of the learnable parameters present in a neural network

Learn how network training is improved by regularization and batch normalization