Book Image

Advanced Deep Learning with Python

By : Ivan Vasilev
Book Image

Advanced Deep Learning with Python

By: Ivan Vasilev

Overview of this book

In order to build robust deep learning systems, you’ll need to understand everything from how neural networks work to training CNN models. In this book, you’ll discover newly developed deep learning models, methodologies used in the domain, and their implementation based on areas of application. You’ll start by understanding the building blocks and the math behind neural networks, and then move on to CNNs and their advanced applications in computer vision. You'll also learn to apply the most popular CNN architectures in object detection and image segmentation. Further on, you’ll focus on variational autoencoders and GANs. You’ll then use neural networks to extract sophisticated vector representations of words, before going on to cover various types of recurrent networks, such as LSTM and GRU. You’ll even explore the attention mechanism to process sequential data without the help of recurrent neural networks (RNNs). Later, you’ll use graph neural networks for processing structured data, along with covering meta-learning, which allows you to train neural networks with fewer training samples. Finally, you’ll understand how to apply deep learning to autonomous vehicles. By the end of this book, you’ll have mastered key deep learning concepts and the different applications of deep learning models in the real world.
Table of Contents (17 chapters)
Free Chapter
1
Section 1: Core Concepts
3
Section 2: Computer Vision
8
Section 3: Natural Language and Sequence Processing
12
Section 4: A Look to the Future

Introducing transfer learning

Let's say that we want to train a model on a task that doesn't have readily available labeled training data like ImageNet does. Labeling training samples could be expensive, time-consuming, and error-prone. So, what does a humble engineer do when they want to solve a real ML problem with limited resources? Enter Transfer Learning (TL).

TL is the process of applying an existing trained ML model to a new, but related, problem. For example, we can take a network trained on ImageNet and repurpose it to classify grocery store items. Alternatively, we could use a driving simulator game to train a neural network to drive a simulated car and then use the network to drive a real car (but don't try this at home!). TL is a general ML concept that's applicable to all ML algorithms, but in this context, we'll talk about CNNs. Here&apos...