Sale!

Perceptrons Reissue of the 1988 Expanded Edition with a new foreword by Leon Bottou An Introduction to Computational Geometry 1st Edition by Marvin Minsky, Seymour A Papert ISBN 0262343932 9780262343930

Original price was: $50.00.Current price is: $35.00.

Perceptrons Reissue of the 1988 Expanded Edition with a new foreword by Léon Bottou An Introduction to Computational Geometry Marvin Minsky Digital Instant Download

Author(s): Marvin Minsky, Seymour A. Papert
ISBN(s): 9780262343930, 0262343932
File Details: PDF, 11.61 MB
Year: 2017
Language: english
SKU: EB-43008430 Category: Tags: ,

Perceptrons Reissue of the 1988 Expanded Edition with a new foreword by Léon Bottou An Introduction to Computational Geometry 1st Edition by Marvin Minsky, Seymour A Papert – Ebook PDF Instant Download/Delivery: 0262343932, 9780262343930
Full download Perceptrons Reissue of the 1988 Expanded Edition with a new foreword by Léon Bottou An Introduction to Computational Geometry 1st Edition after payment

Product details:

ISBN 10: 0262343932 
ISBN 13: 9780262343930
Author: Marvin Minsky, Seymour A Papert

The first systematic study of parallelism in computation by two pioneers in the field.

Reissue of the 1988 Expanded Edition with a new foreword by Léon Bottou

In 1969, ten years after the discovery of the perceptron—which showed that a machine could be taught to perform certain tasks using examples—Marvin Minsky and Seymour Papert published Perceptrons, their analysis of the computational capabilities of perceptrons for specific tasks. As Léon Bottou writes in his foreword to this edition, “Their rigorous work and brilliant technique does not make the perceptron look very good.” Perhaps as a result, research turned away from the perceptron. Then the pendulum swung back, and machine learning became the fastest-growing field in computer science. Minsky and Papert’s insistence on its theoretical foundations is newly relevant.

Perceptrons—the first systematic study of parallelism in computation—marked a historic turn in artificial intelligence, returning to the idea that intelligence might emerge from the activity of networks of neuron-like entities. Minsky and Papert provided mathematical analysis that showed the limitations of a class of computing machines that could be considered as models of the brain. Minsky and Papert added a new chapter in 1987 in which they discuss the state of parallel computers, and note a central theoretical challenge: reaching a deeper understanding of how “objects” or “agents” with individuality can emerge in a network. Progress in this area would link connectionism with what the authors have called “society theories of mind.”

Perceptrons Reissue of the 1988 Expanded Edition with a new foreword by Léon Bottou An Introduction to Computational Geometry 1st Table of contents:

1: Introduction

1.1 The Problem of Perceptrons
1.2 A Brief Overview of the Field of Artificial Intelligence
1.3 Minsky and Papert’s Thesis: What Perceptrons Can and Cannot Do
1.4 The Structure and Goals of the Book

2: The Perceptron Model

2.1 Defining the Perceptron
2.2 The Architecture of a Perceptron: Neurons and Layers
2.3 How a Perceptron Functions: Inputs, Weights, and Activation
2.4 The Perceptron Learning Rule: Gradient Descent
2.5 Limitations of the Perceptron: What Can’t Be Learned
2.6 The XOR Problem: A Classic Example of Perceptron Limitations

3: Geometry of the Perceptron

3.1 Computational Geometry: The Role of Geometric Thinking
3.2 Linear Separability in the Plane
3.3 Geometric Interpretations of Perceptron Learning
3.4 Convexity and Convex Hulls
3.5 A Geometric Analysis of Perceptron Learning Efficiency
3.6 The Role of Linear Boundaries in High-Dimensional Spaces

4: Limitations of the Perceptron

4.1 The Halting Problem: Why Some Problems Are Inherently Unsolvable
4.2 The XOR Problem and its Implications for Neural Networks
4.3 What Perceptrons Cannot Learn: Nonlinear Decision Boundaries
4.4 The Proof of the Inability to Learn Certain Classes of Functions
4.5 A More Generalized View of the Perceptron’s Weaknesses

5: The Dual Problem: Linear Separability

5.1 Linear Separability in Higher Dimensions
5.2 A Generalized Framework for Linear Decision Boundaries
5.3 The Role of Dimensionality in Perceptron Performance
5.4 Applications and Problems in High-Dimensional Spaces
5.5 The Challenge of Generalization: Overfitting and Bias

6: Extensions and Alternatives to the Perceptron

6.1 The Multi-Layer Perceptron: Introducing Hidden Layers
6.2 The Backpropagation Algorithm and its Relevance to Perceptrons
6.3 Nonlinear Activation Functions and Their Impact
6.4 Support Vector Machines: A Comparison to Perceptrons
6.5 Alternatives to Perceptrons: Logical Neurons and Decision Trees

7: Theories of Learning and Adaptive Systems

7.1 Learning in the Context of Perceptrons
7.2 Adaptive Systems: How Machines Can Improve Over Time
7.3 The Role of Feedback in Neural Network Training
7.4 Comparing Perceptrons with Other Learning Algorithms
7.5 Learning as a Process of Optimization and Error Minimization

8: The History and Impact of Perceptrons

8.1 The Origins of Neural Network Research: Early Ideas
8.2 Minsky and Papert’s Impact on AI and Neural Networks
8.3 Criticism and Controversy: The “AI Winter”
8.4 The Resurgence of Neural Networks in the 21st Century
8.5 Modern Deep Learning: Building on the Foundations of Perceptrons

People also search for Perceptrons Reissue of the 1988 Expanded Edition with a new foreword by Léon Bottou An Introduction to Computational Geometry 1st:

    
perceptron 1958
    
perceptron rosenblatt paper
    
perceptron paper
    
1957 perceptron
    
perceptron rosenblatt

Tags: Marvin Minsky, Seymour A Papert, Perceptrons Reissue