- Hardcover: 272 pages
- Publisher: Academic Press; 1 edition (November 21, 2013)
- Language: English
- ISBN-10: 012410407X
- ISBN-13: 978-0124104075
- Product Dimensions: 6 x 0.7 x 9 inches
- Shipping Weight: 1.2 pounds (View shipping rates and policies)
- Average Customer Review: 2 customer reviews
- Amazon Best Sellers Rank: #2,699,833 in Books (See Top 100 in Books)
Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
Calculus of Thought: Neuromorphic Logistic Regression in Cognitive Machines 1st Edition
Use the Amazon App to scan ISBNs and compare prices.
This month's Book With Buzz: "The Lying Game" by Ruth Ware
From the instant New York Times bestselling author of blockbuster thrillers "In a Dark, Dark Wood" and "The Woman in Cabin 10" comes Ruth Ware’s chilling new novel, "The Lying Game." See more
"…Rice argues that cognitive machines will need to be neuromorphic, that is, based upon neuroscience, in order to simulate aspects of human cognition. He sets out the most fundamental and important concepts in modern cognitive neuroscience, including neural dynamics, implicit and explicit learning, neural synchrony, Hebbian spike-timing dependent plasticity, and neural Darwinism."--ProtoView.com, February 2014
From the Back Cover
Calculus of Thought: Neuromorphic Logistic Regression in Cognitive Machines is a must read for all scientists about a very simple computation method designed to simulate big data neural processing. This book is inspired by the Calculus Ratiocinator idea of Gottfried Leibniz which is that machine computation should be developed to simulate human cognitive processes and thus avoid problematic subjective bias in analytic solutions to practical and scientific problems. The Reduced Error Logistic Regression (RELR) method is proposed to be such a Calculus of Thought, as this book reviews how RELR’s completely automated processing may parallel important aspects of both explicit and implicit learning in neural processes. The fact that RELR is really just a simple adjustment to already widely used logistic regression is emphasized, along with RELR’s new applications that go well beyond standard logistic regression in both prediction and explanation. Particular attention is given to how RELR solves some of the most basic problems in today’s big and small data related to high dimensionality, multicollinearity and cognitive bias in capricious outcomes often involving human behavior.
- Provides a high level introduction with detailed reviews of the neural, statistical and machine learning knowledge base as a foundation for this new era of smarter machines.
- Argues that smarter machine learning to handle both explanation and prediction without cognitive bias must have a foundation in cognitive neuroscience and embody similar explicit and implicit learning principles that occur in the brain.
Daniel M. Rice, Ph.D. is the Principal and Senior Scientist and founder of Rice Analytics in St Louis, Missouri. He is both a cognitive neuroscientist and statistician and has been practicing advanced analytic science in either medical, academic or industry settings for his entire career. Dan is a previous recipient of an Individual National Research Service Award from the National Institutes of Health and is author of more than 20 academic and industry publications in cognitive neuroscience, statistics, machine learning, and analytics. In the early 1990’s, he was the lead author on two papers that related explicit memory performance and temporal lobe brain measures to make the initial discovery and claim that Alzheimer’s disease must have an average preclinical causal period of at least 10 years. Since that time, he has worked to develop automated machine learning methods that simulate basic explicit and implicit cognitive neural processes and allow most likely solutions that avoid traditional problems related to error and bias.
Browse award-winning titles. See more
Top customer reviews
The tour-de-force, however, is Rice's integration of psychometrics--especially consideration of measurement error--into the realm of predictive modeing. The book is worth purchasing for this reason alone, Riee convincely demonstrates the advantages of his Reduced Error Logistic Regression (RELR) modeling approach over standard approaches, and many readers will have not had exposure to this aspect of improving predictive models.
For advanced practitioners, the book offers a thoughtul analysis of a thorny issue within predictive modeling, that of attribute selection How can we predict well when we don't use the most appropriate atributes to do so? Rice argues that RELR can be used to provide a rational approach to attiribute selecition, in a way that addresses oft-ignored pschometric issues.
Calculus of Thought gives the predicitve modeling reader some badly needed ammunition:: reasons for doing predictive modeling in a certain way. The first set of reasons are psychometric, the second set of reasons are conceptual, dealing with how the human neurocognitive system addresses prediction. Imagine it-going to your boss and explaining that you are addressing both short-term and long-term aspects of your predictive model because--after all--that's what the human brain does. When your boss complains, you can explain that doing so helps move predictive modeling from craftsmanship to science--and Rice will have succeeded in his mission.
--Jeffrey P. schwartz, PhD, Cognitive Scientist