Overview

Learn about fundamental deep learning architectures such as CNNs, RNNs, LSTMs, and GRUs for modeling image and sequential data.

Learn Deep Learning

Deep learning is a rapidly evolving field of artificial intelligence that revolutionized the field of machine learning, enabling breakthroughs in areas such as computer vision, natural language processing, and speech recognition. The most recent advances in Generative AI, including image generators and conversational chatbots, have brought deep machine learning models to the public spotlight. Start learning about how deep learning works and how to train deep models yourself today.

Use PyTorch, the Most Pythonic Way to Do Deep Learning

PyTorch is a powerful and flexible deep learning framework that allows researchers and practitioners to build and train neural networks with ease. Loved by Pythonistas around the world, PyTorch offers a lot of flexibility and an intuitive way to implement deep learning concepts.

Train Robust Deep Learning Models

This course in deep learning with PyTorch is designed to provide you with a comprehensive understanding of the fundamental concepts and techniques of deep learning, and equip you with the practical skills to implement various neural network concepts. You’ll get to grips with multi-input and multi-output architectures. You’ll learn how to prevent the vanishing and exploding gradients problems using non-saturating activations, batch normalization, and proper weights initialization. You will be able to alleviate overfitting using regularization and dropout. Finally, you will know how to accelerate the training process with learning rate scheduling.

Build Image and Sequence Models

You get to know two specialized neural network architectures: Convolutional Neural Networks (CNNs) for image data and Recurrent Neural Networks (RNNs) for sequential data such as time series or text. You will understand their advantages and will be able to implement them in image classification and time series prediction tasks.

By the end of the course, you will have the knowledge and confidence to robustly train and evaluate your own deep learning models for a range of applications.

Syllabus

Training Robust Neural Networks

Learn how to train neural networks in a robust way. In this chapter, you will use object-oriented programming to define PyTorch datasets and models and refresh your knowledge of training and evaluating neural networks. You will also get familiar with different optimizers and, finally, get to grips with various techniques that help mitigate the problems of unstable gradients so ubiquitous in neural nets training.

Images & Convolutional Neural Networks

Train neural networks to solve image classification tasks. In this chapter, you will learn how to handle image data in PyTorch and get to grips with convolutional neural networks (CNNs). You will practice training and evaluating an image classifier while learning about how to improve the model performance with data augmentation.

Sequences & Recurrent Neural Networks

Build and train recurrent neural networks (RNNs) for processing sequential data such as time series, text, or audio. You will learn about the two most popular recurrent architectures, Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, as well as how to prepare sequential data for model training. You will practice your skills by training and evaluating a recurrent model for predicting electricity consumption.

Multi-Input & Multi-Output Architectures

Build multi-input and multi-output models, demonstrating how they can handle tasks requiring more than one input or generating multiple outputs. You will explore how to design and train these models using PyTorch and delve into the crucial topic of loss weighting in multi-output models. This involves understanding how to balance the importance of different tasks when training a model to perform multiple tasks simultaneously.