Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
8,875,208
result(s) for
"NETWORK"
Sort by:
The Structure and Dynamics of Networks
From the Internet to networks of friendship, disease transmission, and even terrorism, the concept--and the reality--of networks has come to pervade modern society. But what exactly is a network? What different types of networks are there? Why are they interesting, and what can they tell us? In recent years, scientists from a range of fields--including mathematics, physics, computer science, sociology, and biology--have been pursuing these questions and building a new \"science of networks.\" This book brings together for the first time a set of seminal articles representing research from across these disciplines. It is an ideal sourcebook for the key research in this fast-growing field.
The book is organized into four sections, each preceded by an editors' introduction summarizing its contents and general theme. The first section sets the stage by discussing some of the historical antecedents of contemporary research in the area. From there the book moves to the empirical side of the science of networks before turning to the foundational modeling ideas that have been the focus of much subsequent activity. The book closes by taking the reader to the cutting edge of network science--the relationship between network structure and system dynamics. From network robustness to the spread of disease, this section offers a potpourri of topics on this rapidly expanding frontier of the new science.
eBook
Advanced deep learning with TensorFlow 2 and Keras : apply DL, GANs, VAEs, deep RL, unsupervised learning, object detection and segmentation, and more
A second edition of the bestselling guide to exploring and mastering deep learning with Keras, updated to include TensorFlow 2.x with new chapters on object detection, semantic segmentation, and unsupervised learning using mutual information.
eBook
NTP security : a quick-start guide
\"Learn the risks associated with Network Time Protocol (NTP) security and how to minimize those risks in daily deployment. Disruption of NTP services can interrupt communication between servers on the network and take an entire network offline. Beyond disrupting communication, flaws in the NTP daemon itself can make servers vulnerable to external attack--attacks that often go unnoticed. NTP is being used more frequently in Distributed Denial of Service (DDoS) attacks. It is a User Datagram Protocol (UDP) with encryption schemes that are not often used or are poorly implemented, making it susceptible to spoofing. Despite all of the security challenges, the fact is that NTP is critical to most modern networks. It is one of those \"set it and forget it\" protocols that network administrators and even security professionals don't understand in depth. However, an attacker who does understand the security flaws can wreak havoc on an insecure network. NTP Security: A Quick-Start Guide provides a deeper understanding of the protocol itself and how to deploy a strategy using the protocol throughout a network in a secure manner. Your security team will be able to provide better guidance to the system and network teams who will then be able to better manage the day-to-day implementation. This succinct resource offers practical guidance to an underserved topic (actually, not served at all). Coverage includes: an understanding of NTP and the importance of time synchronization in modern networks; issues in NTP security, including an analysis of NTP traffic; a review of the vulnerabilities and flaws in the protocol; practical solutions for securing NTP and building a robust infrastructure; effective alternatives to NTP\"--Back cover.
Book
Neural control engineering : the emerging intersection between control theory and neuroscience
How powerful new methods in nonlinear control engineering can be applied to neuroscience, from fundamental model formulation to advanced medical applications.Over the past sixty years, powerful methods of model-based control engineering have been responsible for such dramatic advances in engineering systems as autolanding aircraft, autonomous vehicles, and even weather forecasting. Over those same decades, our models of the nervous system have evolved from single-cell membranes to neuronal networks to large-scale models of the human brain. Yet until recently control theory was completely inapplicable to the types of nonlinear models being developed in neuroscience. The revolution in nonlinear control engineering in the late 1990s has made the intersection of control theory and neuroscience possible. In Neural Control Engineering, Steven Schiff seeks to bridge the two fields, examining the application of new methods in nonlinear control engineering to neuroscience. After presenting extensive material on formulating computational neuroscience models in a control environment-including some fundamentals of the algorithms helpful in crossing the divide from intuition to effective application-Schiff examines a range of applications, including brain-machine interfaces and neural stimulation. He reports on research that he and his colleagues have undertaken showing that nonlinear control theory methods can be applied to models of single cells, small neuronal networks, and large-scale networks in disease states of Parkinson's disease and epilepsy. With Neural Control Engineering the reader acquires a working knowledge of the fundamentals of control theory and computational neuroscience sufficient not only to understand the literature in this trandisciplinary area but also to begin working to advance the field. The book will serve as an essential guide for scientists in either biology or engineering and for physicians who wish to gain expertise in these areas.
eBook
Survey of Deep Learning Paradigms for Speech Processing
Over the past decades, a particular focus is given to research on machine learning techniques for speech processing applications. However, in the past few years, research has focused on using deep learning for speech processing applications. This new machine learning field has become a very attractive area of study and has remarkably better performance than the others in the various speech processing applications. This paper presents a brief survey of application deep learning for various speech processing applications such as speech separation, speech enhancement, speech recognition, speaker recognition, emotion recognition, language recognition, music recognition, speech data retrieval, etc. The survey goes on to cover the use of Auto-Encoder, Generative Adversarial Network, Restricted Boltzmann Machine, Deep Belief Network, Deep Neural Network, Convolutional Neural Network, Recurrent Neural Network and Deep Reinforcement Learning for speech processing. Additionally, it focuses on the various speech database and evaluation metrics used by deep learning algorithms for performance evaluation.
Journal Article