{"id":16062,"date":"2026-08-10T12:02:49","date_gmt":"2026-08-10T12:02:49","guid":{"rendered":"https:\/\/nokobox.com\/index.php\/item\/the-massachusetts-institute-of-technology-deep-learning-mit-press-essential-knowledge-series-2019\/"},"modified":"2026-08-10T12:02:49","modified_gmt":"2026-08-10T12:02:49","slug":"the-massachusetts-institute-of-technology-deep-learning-mit-press-essential-knowledge-series-2019","status":"publish","type":"digital_item","link":"https:\/\/nokobox.com\/index.php\/item\/the-massachusetts-institute-of-technology-deep-learning-mit-press-essential-knowledge-series-2019\/","title":{"rendered":"The Massachusetts Institute of Technology \u2013 Deep Learning: MIT Press Essential Knowledge Series 2019"},"content":{"rendered":"
\n

Description<\/span><\/h2>\n

In Deep Learning: MIT Press Essential Knowledge Series, computer scientist John D. Kelleher offers a very affordable, concise, yet comprehensive guide to deep learning. The technology forms the core of modern artificial intelligence and has enabled features such as machine vision, speech recognition on mobile phones, machine translation, and self-driving cars. The author explains how these systems enable data-driven decision-making by extracting patterns from big data.<\/span><\/p>\n

Without going into the tedious mathematical complexities, the audiobook explains the enduring concepts, the history of developments, and the current state of the science. Kalhor describes the basic structures of neural networks, such as autoencoders and recurrent neural networks, and moves on to new phenomena, such as generative adversarial networks (GANs). In this work, the listener is introduced to the two fundamental algorithms, \u201cgradient descent\u201d and \u201cback propagation,\u201d in a completely understandable language, and finally examines the challenges and future prospects of this technology.<\/span><\/p>\n

Book Features<\/span><\/h3>\n