Vtome.ru - электронная библиотека

Cloud-based Multi-Modal Information Analytics: A Hands-on Approach

  • Добавил: literator
  • Дата: 10-05-2023, 07:10
  • Комментариев: 0
Cloud-based Multi-Modal Information Analytics: A Hands-on ApproachНазвание: Cloud-based Multi-Modal Information Analytics: A Hands-on Approach
Автор: Srinidhi Hiriyannaiah, Siddesh G.M., Srinivasa K.G.
Издательство: CRC Press
Год: 2023
Страниц: 257
Язык: английский
Формат: pdf (true)
Размер: 34.7 MB

Cloud based Multi-Modal Information Analytics: A Hands-on Approach discusses the various modalities of data and provide an aggregated solution using cloud. It includes the fundamentals of neural networks, different types and how they can be used for the multi-modal information analytics. The various application areas that are image-centric and videos are also presented with deployment solutions in the cloud.

Deep Learning (DL) applications are based on neural networks for learning and prediction for various problems of Computer Vision, self-driving, speech translation and other applications. Neural networks are the mathematical models inspired by the human brain that facilitate learning and prediction. Neural networks play an important role in Deep Learning and its various applications. Large deep networks consist of neural networks as the core component for the tasks of classification and others. Artificial neural network (ANN) forms the basis for various neural networks. It provides a representation and the architecture for Deep Learning applications.

PyTorch is an open source library for implementing programs on computer vision and multimodal data. It supports all operating systems with a primary focus on the interface of Python. There are a wide number of applications built on PyTorch, which include Tesla Autopilot, Uber’s Pyro, Hugging Face’s Transformers, PyTorch Lightning and Catalyst. The major features of PyTorch are listed as follows:

• Interface: It offers easy and usable interface that runs on Python. It uses the services of Python and its framework in a useful way for implementation.
• Computational graphs: It uses the computational graph as the background for the execution of tasks. It also gives the option of changing it during run time dynamically.
• Abstractions: It provides three levels of abstraction, namely tensor, variable and module. Tensor is used for the creation of n- dimensional array, variable is used for the computational graph, and module is used for storing the learnable weights.

PyTorch offers numerous options for the implementation of various Machine Learning and Deep Learning modules. We discuss some of the examples related to PyTorch next.

Features:

Life cycle of the multi- modal data analytics is discussed with applications of modalities of text, image, and video.
Deep Learning fundamentals and architectures covering convolutional Neural Networks, recurrremt neural networks, and types of learning for different multi-modal networks.
Applications of Multi-Modal Analytics covering Text , Speech, and Image.
This book is aimed at researchers in Multi-modal analytics and related areas

Contents:


Скачать Cloud-based Multi-Modal Information Analytics: A Hands-on Approach












ОТСУТСТВУЕТ ССЫЛКА/ НЕ РАБОЧАЯ ССЫЛКА ЕСТЬ РЕШЕНИЕ, ПИШИМ СЮДА!


ПРАВООБЛАДАТЕЛЯМ


СООБЩИТЬ ОБ ОШИБКЕ ИЛИ НЕ РАБОЧЕЙ ССЫЛКЕ



Внимание
Уважаемый посетитель, Вы зашли на сайт как незарегистрированный пользователь.
Мы рекомендуем Вам зарегистрироваться либо войти на сайт под своим именем.
Информация
Посетители, находящиеся в группе Гости, не могут оставлять комментарии к данной публикации.