Gradient Expectations

An insightful investigation into the mechanisms underlying the predictive functions of neural networks—and their ability to chart a new path for AI.Prediction is a cognitive advantage like few others, inherently linked to our ability to survive and thrive. Our brains are awash in signals that embody...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Downing, Keith L.
التنسيق: Online
اللغة:الإنجليزية
منشور في: The MIT Press 2023
الموضوعات:
الوصول للمادة أونلاين:ONIX_20230731_9780262374675_33
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1869528236842549248
author Downing, Keith L.
author_browse Downing, Keith L.
author_facet Downing, Keith L.
author_sort Downing, Keith L.
collection Directory of Open Access Books
description An insightful investigation into the mechanisms underlying the predictive functions of neural networks—and their ability to chart a new path for AI.Prediction is a cognitive advantage like few others, inherently linked to our ability to survive and thrive. Our brains are awash in signals that embody prediction. Can we extend this capability more explicitly into synthetic neural networks to improve the function of AI and enhance its place in our world? Gradient Expectations is a bold effort by Keith L. Downing to map the origins and anatomy of natural and artificial neural networks to explore how, when designed as predictive modules, their components might serve as the basis for the simulated evolution of advanced neural network systems.Downing delves into the known neural architecture of the mammalian brain to illuminate the structure of predictive networks and determine more precisely how the ability to predict might have evolved from more primitive neural circuits. He then surveys past and present computational neural models that leverage predictive mechanisms with biological plausibility, identifying elements, such as gradients, that natural and artificial networks share. Behind well-founded predictions lie gradients, Downing finds, but of a different scope than those that belong to today's deep learning. Digging into the connections between predictions and gradients, and their manifestation in the brain and neural networks, is one compelling example of how Downing enriches both our understanding of such relationships and their role in strengthening AI tools. Synthesizing critical research in neuroscience, cognitive science, and connectionism, Gradient Expectations offers unique depth and breadth of perspective on predictive neural-network models, including a grasp of predictive neural circuits that enables the integration of computational models of prediction with evolutionary algorithms.
format Online
id doab-20.500.12854ir-111599
institution Directory of Open Access Books
language eng
publishDate 2023
publishDateRange 2023
publishDateSort 2023
publisher The MIT Press
publisherStr The MIT Press
record_format ojs
spelling doab-20.500.12854ir-1115992024-04-14T10:28:27Z Gradient Expectations Downing, Keith L. Computer Science/Artificial Intelligence thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQN Neural networks and fuzzy systems thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQM Machine learning thema EDItEUR::G Reference, Information and Interdisciplinary subjects::GT Interdisciplinary studies::GTK Cognitive studies An insightful investigation into the mechanisms underlying the predictive functions of neural networks—and their ability to chart a new path for AI.Prediction is a cognitive advantage like few others, inherently linked to our ability to survive and thrive. Our brains are awash in signals that embody prediction. Can we extend this capability more explicitly into synthetic neural networks to improve the function of AI and enhance its place in our world? Gradient Expectations is a bold effort by Keith L. Downing to map the origins and anatomy of natural and artificial neural networks to explore how, when designed as predictive modules, their components might serve as the basis for the simulated evolution of advanced neural network systems.Downing delves into the known neural architecture of the mammalian brain to illuminate the structure of predictive networks and determine more precisely how the ability to predict might have evolved from more primitive neural circuits. He then surveys past and present computational neural models that leverage predictive mechanisms with biological plausibility, identifying elements, such as gradients, that natural and artificial networks share. Behind well-founded predictions lie gradients, Downing finds, but of a different scope than those that belong to today's deep learning. Digging into the connections between predictions and gradients, and their manifestation in the brain and neural networks, is one compelling example of how Downing enriches both our understanding of such relationships and their role in strengthening AI tools. Synthesizing critical research in neuroscience, cognitive science, and connectionism, Gradient Expectations offers unique depth and breadth of perspective on predictive neural-network models, including a grasp of predictive neural circuits that enables the integration of computational models of prediction with evolutionary algorithms. 2023-07-31T10:54:58Z 2023-07-31T10:54:58Z 2023 book ONIX_20230731_9780262374675_33 9780262374675 9780262545617 https://directory.doabooks.org/handle/20.500.12854/111599 eng The MIT Press image/jpeg n/a https://doi.org/10.7551/mitpress/14723.001.0001 The MIT Press The MIT Press 10.7551/mitpress/14723.001.0001 10.7551/mitpress/14723.001.0001 ae0cf962-f685-4933-93d1-916defa5123d 9780262374675 9780262545617 The MIT Press 224 Cambridge open access
spellingShingle Computer Science/Artificial Intelligence
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQN Neural networks and fuzzy systems
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQM Machine learning
thema EDItEUR::G Reference, Information and Interdisciplinary subjects::GT Interdisciplinary studies::GTK Cognitive studies
Downing, Keith L.
Gradient Expectations
title Gradient Expectations
title_full Gradient Expectations
title_fullStr Gradient Expectations
title_full_unstemmed Gradient Expectations
title_short Gradient Expectations
title_sort gradient expectations
topic Computer Science/Artificial Intelligence
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQN Neural networks and fuzzy systems
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQM Machine learning
thema EDItEUR::G Reference, Information and Interdisciplinary subjects::GT Interdisciplinary studies::GTK Cognitive studies
topic_facet Computer Science/Artificial Intelligence
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQN Neural networks and fuzzy systems
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQM Machine learning
thema EDItEUR::G Reference, Information and Interdisciplinary subjects::GT Interdisciplinary studies::GTK Cognitive studies
url ONIX_20230731_9780262374675_33
work_keys_str_mv AT downingkeithl gradientexpectations