Skip to main content

Ctrl+K

Classical Foundations of Artificial Neural Networks

Classical Foundations of Artificial Neural Networks

Part I: Origins

Chapter 1: The McCulloch-Pitts Neuron (1943)
Chapter 2: Building Logic from Neurons
Chapter 3: Historical Context and Timeline

Part II: The Perceptron

Chapter 4: Rosenblatt’s Perceptron
Chapter 5: The Perceptron Learning Algorithm
Chapter 6: The Perceptron Convergence Theorem
Chapter 7: What Perceptrons Can Compute

Part III: Limitations and Breakthroughs

Chapter 8: The XOR Problem
Chapter 9: Minsky and Papert’s Analysis
Chapter 10: Linear Separability — A Deep Dive
Chapter 11: Breaking Through — Multi-Layer Networks

Part IV: Learning Rules

Chapter 12: Hebbian Learning Theory
Chapter 13: Oja’s Rule and Principal Component Analysis
Chapter 14: The Zoo of Learning Rules

Part V: Backpropagation

Chapter 15: Gradient Descent Foundations
Chapter 16: Backpropagation – The Complete Derivation
Chapter 17: Activation Functions and the Vanishing Gradient
Chapter 18: Implementing Backpropagation from Scratch
Chapter 19: The Universal Approximation Theorem

Part VI: Synthesis

Chapter 20: From McCulloch-Pitts to Backpropagation – The Complete Arc
Appendix: Complete Bibliography and Reading Guide

Index

By Bartosz Naskręcki

© Copyright 2026 Bartosz Naskręcki (co-generated with Claude).