• This course is designed for anyone interested to get started with using PyTorch and build Artificial Neural Networks. It is geared towards Data Scientists, Data Engineers, Software Engineers, Software Architects, Quality Assurance Engineers.

• Basic knowledge of python and fundamentals of Machines Learning.

Topic Outline:

PyTorch Introduction

• Machine Learning v/s Deep Learning what’s the difference?
• General information about PyTorch
• Lab: Quick review of NumPy and Pandas

Working with Tensors

• What are tensors?
• Creating Tensors
• Getting Tensor Attributes
• Manipulating Tensors
• Operations on Tensors
• NumPy & Tensors
• Hands-on lab with Tensors

Using PyTorch for Artificial Neural Network – Regression

• Learn to build a neural network for a regression problem
• Understand the basics of building a PyTorch model
• Selecting the loss and the optimizers for the model
• Handling categorical and datetime data
• Understand the use of metrices
• Hands-on labs with ANN for Regression

Using PyTorch for Artificial Neural Network – Classification

• Build a neural network for a classification problem
• Learn about the loss functions, metrics and optimizers used for Classification
• Hands-on lab with ANN for Classification

Convolutional Neural Networks with PyTorch

• Understand basic terminology of Convolutional Neural Network (CNN)
• Understand how to build a image processing model using ANN
• Build a CNN model on the same data set as above
• Hands-on lab with ANN and CNN for image processing

Hands-on Lab: Instructions will be provided to install Anaconda and PyTorch on student’s machines.