Deep Learning with Python and PyTorch (edX)

NOTE: In order to be successful in completing this course, please ensure you are familiar with PyTorch Basics and have practical knowledge to apply it to Machine Learning. If you do not have this pre-requiste knowledge, it is highly recommended you complete the PyTorch Basics for Machine Learning course prior to starting this course.

You will first review multiclass classification, learning how to build and train a multiclass linear classifier in PyTorch. This will be followed by an in-depth introduction on how to construct Feed-forward neural networks in PyTorch, learning how to train these models, how to adjust hyperparameters such as activation functions and the number of neurons.

You will then learn how to build and train deep neural networks—learning how to apply methods such as dropout, initialization, different types of optimizers and batch normalization. We will then focus on Convolutional Neural Networks, training your model on a GPU and Transfer Learning (pre-trained models). You will finally learn about dimensionality reduction and autoencoders. Including principal component analysis, data whitening, shallow autoencoders, deep autoencoders, transfer learning with autoencoders, and autoencoder applications.

Finally, you will test your skills in a final project.

This course is part of the Deep Learning Professional Certificate.

What you'll learn

- Apply knowledge of Deep Neural Networks and related machine learning methods

- Build and Train Deep Neural Networks using PyTorch

- Build Deep learning pipelines

Syllabus

Module 1 - Classification

- Softmax Regression

- Softmax in PyTorch Regression

- Training Softmax in PyTorch Regression

Module 2 - Neural Networks

- Introduction to Networks

- Network Shape Depth vs Width

- Back Propagation

- Activation functions

Module 3 - Deep Networks

- Dropout

- Initialization

- Batch normalization

- Other optimization methods

Module 4 - Computer Vision Networks

- Convolution

- Max Polling

- Convolutional Networks

- Pre-trained Networks

Module 5 - Computer Vision Networks

- Convolution

- Max Pooling

- Convolutional Networks

- Training your model with a GPU

- Pre-trained Networks

Module 6 Dimensionality reduction and autoencoders

- Principle component analysis

- Linear autoencoders

- Autoencoders

- Transfer learning

- Deep Autoencoders

Module 7 -Independent Project