Название: Multi-faceted Deep Learning: Models and Data
Автор: Jenny Benois-Pineau, Akka Zemmari
Издательство: Springer
Год: 2021
Страниц: 321
Язык: английский
Формат: pdf (true), epub
Размер: 28.6 MB

This book covers a large set of methods in the field of Artificial Intelligence - Deep Learning applied to real-world problems. The fundamentals of the Deep Learning approach and different types of Deep Neural Networks (DNNs) are first summarized in this book, which offers a comprehensive preamble for further problem–oriented chapters. The most interesting and open problems of machine learning in the framework of Deep Learning are discussed in this book and solutions are proposed. This book illustrates how to implement the zero-shot learning with Deep Neural Network Classifiers, which require a large amount of training data. The lack of annotated training data naturally pushes the researchers to implement low supervision algorithms. Metric learning is a long-term research but in the framework of Deep Learning approaches, it gets freshness and originality. Fine-grained classification with a low inter-class variability is a difficult problem for any classification tasks. This book presents how it is solved, by using different modalities and attention mechanisms in 3D convolutional networks.

The book starts by introducing the design and implementation of various architectures for Deep Learning, together with optimization algorithms. It discusses the most state-of-the-art networks, such as Artificial Neural Networks, Convolutional Neural Networks and Recurrent Networks. Then it presents some other models like Generative Neural Networks, Autoencoders and Siamese CNNs.

As a first application of Deep Learning methods, we consider its use for semantic segmentation. A chapter reviews the image semantic segmentation task and recent advanced strategies to face typical training issues (few training samples, specific data, strong target imbalance, …) in a variety of application domains. Another chapter considers image and video captioning using deep learning. It aims at giving insights on how to generate descriptive sentences from images and videos. A third application investigates the use of the 3D Convolutional Neural Networks for action recognition with application to sport gesture recognition.

As mentioned above, the impressive success of Deep Learning is due to the huge amount of available data. However, for supervised learning, this data have to be labeled. In a dedicated chapter, we present solutions based on three families of methods for learning with less expensive labelling.

Researchers focused on Machine Learning, Deep learning, Multimedia and Computer Vision will want to buy this book. Advanced level students studying computer science within these topic areas will also find this book useful.