The Perceptron

The Perceptron is a good July 1 starting point because it gives learners the original linear-classifier idea before modern depth, attention, or scale enter the story.

Reading focus: How a weighted input rule turns examples into a learned decision boundary. Why early neural-network optimism centered on simple trainable units. What limitations later architectures had to overcome.

Psychological Review 1958. Frank Rosenblatt. 30 min read, very easy difficulty.