Reliable Reasoning

Induction and Statistical Learning Theory

Look inside
Paperback
$25.00 US
On sale Jan 13, 2012 | 118 Pages | 9780262517348
The implications for philosophy and cognitive science of developments in statistical learning theory.

In Reliable Reasoning, Gilbert Harman and Sanjeev Kulkarni—a philosopher and an engineer—argue that philosophy and cognitive science can benefit from statistical learning theory (SLT), the theory that lies behind recent advances in machine learning. The philosophical problem of induction, for example, is in part about the reliability of inductive reasoning, where the reliability of a method is measured by its statistically expected percentage of errors—a central topic in SLT.

After discussing philosophical attempts to evade the problem of induction, Harman and Kulkarni provide an admirably clear account of the basic framework of SLT and its implications for inductive reasoning. They explain the Vapnik-Chervonenkis (VC) dimension of a set of hypotheses and distinguish two kinds of inductive reasoning. The authors discuss various topics in machine learning, including nearest-neighbor methods, neural networks, and support vector machines. Finally, they describe transductive reasoning and suggest possible new models of human reasoning suggested by developments in SLT.

Gilbert Harman is Stuart Professor of Philosophy at Princeton University and the author of Explaining Value and Other Essays in Moral Philosophy and Reasoning, Meaning, and Mind.

Sanjeev Kulkarni is Professor of Electrical Engineering and an associated faculty member of the Department of Philosophy at Princeton University with many publications in statistical learning theory.

About

The implications for philosophy and cognitive science of developments in statistical learning theory.

In Reliable Reasoning, Gilbert Harman and Sanjeev Kulkarni—a philosopher and an engineer—argue that philosophy and cognitive science can benefit from statistical learning theory (SLT), the theory that lies behind recent advances in machine learning. The philosophical problem of induction, for example, is in part about the reliability of inductive reasoning, where the reliability of a method is measured by its statistically expected percentage of errors—a central topic in SLT.

After discussing philosophical attempts to evade the problem of induction, Harman and Kulkarni provide an admirably clear account of the basic framework of SLT and its implications for inductive reasoning. They explain the Vapnik-Chervonenkis (VC) dimension of a set of hypotheses and distinguish two kinds of inductive reasoning. The authors discuss various topics in machine learning, including nearest-neighbor methods, neural networks, and support vector machines. Finally, they describe transductive reasoning and suggest possible new models of human reasoning suggested by developments in SLT.

Author

Gilbert Harman is Stuart Professor of Philosophy at Princeton University and the author of Explaining Value and Other Essays in Moral Philosophy and Reasoning, Meaning, and Mind.

Sanjeev Kulkarni is Professor of Electrical Engineering and an associated faculty member of the Department of Philosophy at Princeton University with many publications in statistical learning theory.

Celebrating 100 years of James Baldwin

In celebration of James Baldwin, the literary legend and civil rights champion, and the centennial of his birth, we are sharing a collection of his work.   James Baldwin (1924–1987) was a novelist, essayist, playwright, poet, and social critic. His first novel, Go Tell It on the Mountain, appeared in 1953 to excellent reviews, and his essay collections Notes

Read more

The New York Times’s 100 Best Books of the 21st Century

The New York Times recently published their list “100 Best Books of the 21st Century.” We are pleased to announce that there are 49 titles published from Penguin Random House and its distribution clients included in this list. Browse our collection of Penguin Random House titles here. Browse the full list from The New York

Read more