Deep Learning in Time Series Analysis
暫譯: 時間序列分析中的深度學習

Gharehbaghi, Arash

Deep Learning in Time Series Analysis
  • 出版商: CRC
  • 出版日期: 2023-07-07
  • 售價: $5,550
  • 貴賓價: 9.5 折 $5,273
  • 語言: 英文
  • 頁數: 196
  • 裝訂: Hardcover - also called cloth, retail trade, or trade
  • ISBN: 0367321785
  • ISBN-13: 9780367321789
  • 相關分類: DeepLearning

    • 海外代購書籍(需單獨結帳)

商品描述

Deep learning is an important element of artificial intelligence, especially in applications such as image classification in which various architectures of neural network, e.g., convolutional neural networks, have yielded reliable results. This book introduces deep learning for time series analysis, particularly for cyclic time series. It elaborates on the methods employed for time series analysis at the deep level of their architectures. Cyclic time series usually have special traits that can be employed for better classification performance. These are addressed in the book. Processing cyclic time series is also covered herein.

An important factor in classifying stochastic time series is the structural risk associated with the architecture of classification methods. The book addresses and formulates structural risk, and the learning capacity defined for a classification method. These formulations and the mathematical derivations will help the researchers in understanding the methods and even express their methodologies in an objective mathematical way. The book has been designed as a self-learning textbook for the readers with different backgrounds and understanding levels of machine learning, including students, engineers, researchers, and scientists of this domain. The numerous informative illustrations presented by the book will lead the readers to a deep level of understanding about the deep learning methods for time series analysis.

商品描述(中文翻譯)

深度學習是人工智慧的重要元素，特別是在圖像分類等應用中，各種神經網絡架構，例如卷積神經網絡，已經產生了可靠的結果。本書介紹了用於時間序列分析的深度學習，特別是針對循環時間序列。它詳細闡述了在其架構的深層次上進行時間序列分析所採用的方法。循環時間序列通常具有特殊的特徵，可以用於提高分類性能。本書將針對這些特徵進行探討。本書還涵蓋了循環時間序列的處理。

在對隨機時間序列進行分類時，一個重要因素是與分類方法架構相關的結構風險。本書針對結構風險進行了探討並進行了公式化，並定義了分類方法的學習能力。這些公式化及其數學推導將幫助研究人員理解這些方法，甚至以客觀的數學方式表達他們的方法論。本書被設計為一本自學教材，適合不同背景和機器學習理解水平的讀者，包括學生、工程師、研究人員和該領域的科學家。本書中提供的眾多資訊性插圖將引導讀者深入理解時間序列分析的深度學習方法。

作者簡介

Arash Gharehbaghi obtained a M.Sc. degree in biomedical engineering from Amir Kabir University, Tehran, Iran, in 2000, an advanced M.Sc. of Telemedia from Mons University, Belgium, and PhD degree of biomedical engineering from Linköping University, Sweden in 2014. He is a researcher at the School of Information Technology, Halmstad University, Sweden. He has conducted several studies on signal processing, machine learning and artificial intelligence over two decades that led to the international patents, and publications in high prestigious scientific journals.

He has proposed new learning methods for learning and validating time series analysis, among which Time-Growing Neural Network, and A-Test are two recent ones that have interested the machine learning community. He won the first prize of young investigator award from the International Federation of Biomedical Engineering in 2014.

作者簡介(中文翻譯)

Arash Gharehbaghi 於2000年獲得伊朗德黑蘭阿米爾卡比爾大學的生物醫學工程碩士學位，隨後在比利時蒙斯大學獲得高級碩士學位（Telemedia），並於2014年在瑞典林雪平大學獲得生物醫學工程博士學位。他目前是瑞典哈爾姆斯塔大學資訊科技學院的研究員。在過去二十年中，他在信號處理、機器學習和人工智慧方面進行了多項研究，並獲得了國際專利，並在高水平的科學期刊上發表了多篇論文。

他提出了新的學習方法來學習和驗證時間序列分析，其中「時間增長神經網絡」（Time-Growing Neural Network）和「A-Test」是最近引起機器學習社群興趣的兩個方法。他於2014年獲得國際生物醫學工程聯合會的青年研究者獎第一名。

類似商品

最後瀏覽商品 (4)