The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain
Abstract¶
If we are eventually to understand the capability of higher organisms for perceptual recognition, generalization, recall, and thinking, we must first have answers to three fundamental questions: 1. How is information about the physical world sensed, or detected, by the biological system? 2. In what form is information stored, or remembered? 3. How does information contained in storage, or in memory, influence recognition and behavior? The first of these questions is in the
Summary¶
Rosenblatt presents the perceptron as a probabilistic model of learning and recognition, connecting neural-style adaptive units to storage, generalization, and behavior. The paper is foundational for neural networks and machine learning because it frames a trainable linear threshold device as both a computational classifier and a model of biological information processing.