{"product_id":"deep-learning-in-time-series-analysis-9780367321789","title":"Deep Learning in Time Series Analysis","description":"\u003cp\u003e\u003c\/p\u003e\u003cblockquote\u003e\n\u003cbr\u003eDeep learning is an essential component of artificial intelligence, particularly in image classification, and this book introduces it for time series analysis, focusing on cyclic time series. It addresses the structural risk associated with classification methods and provides a learning capacity definition. The book is designed as a self-learning textbook for readers with various backgrounds and understanding levels of machine learning. \u003c\/blockquote\u003e\u003cp\u003e\u003cstrong\u003eFormat\u003c\/strong\u003e: Hardback\u003cbr\u003e\u003cstrong\u003eLength\u003c\/strong\u003e: 196 pages\u003cbr\u003e\u003cstrong\u003ePublication date\u003c\/strong\u003e: 07 July 2023\u003cbr\u003e\u003cstrong\u003ePublisher\u003c\/strong\u003e: Taylor \u0026amp; Francis Ltd\u003cbr\u003e\u003c\/p\u003e \u003cp\u003e\u003cbr\u003eDeep learning plays a crucial role in artificial intelligence, particularly in applications like image classification, where various neural network architectures, such as convolutional neural networks, have achieved reliable results. This comprehensive book delves into the realm of deep learning for time series analysis, focusing specifically on cyclic time series. It provides an in-depth exploration of the methods employed at the deep level of these architectures, highlighting the unique characteristics of cyclic time series that can enhance classification performance. The book also covers the processing of cyclic time series, addressing the challenges and techniques involved in analyzing these complex data structures.\u003cbr\u003e\u003cbr\u003eStructural risk, a significant aspect of classifying stochastic time series, is addressed and formulated in the book. It discusses the learning capacity of classification methods and the mathematical derivations that aid researchers in understanding and objectively expressing their methodologies. The book is designed as a self-learning textbook, catering to readers with diverse backgrounds and levels of machine learning expertise, including students, engineers, researchers, and scientists in the field. With its numerous informative illustrations, the book guides readers to a profound understanding of deep learning methods for time series analysis, enabling them to apply these techniques to their own research and applications.\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eWeight\u003c\/strong\u003e: 540g\u003cbr\u003e\u003cstrong\u003eDimension\u003c\/strong\u003e: 234 x 156 (mm)\u003cbr\u003e\u003cstrong\u003eISBN-13\u003c\/strong\u003e: 9780367321789\u003c\/p\u003e","brand":"ArashGharehbaghi","offers":[{"title":"Hardback","offer_id":44348294201594,"sku":"9780367321789","price":133.28,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0522\/4297\/2845\/products\/1689349856829_book.jpg?v=1689442546","url":"https:\/\/shulphink.com\/products\/deep-learning-in-time-series-analysis-9780367321789","provider":"Shulph Ink","version":"1.0","type":"link"}