In 1958, Frank Rosenblatt, a psychologist at the Cornell Aeronautical Laboratory, introduced the perceptron, a type of artificial neural network. The perceptron was designed to simulate the thought processes of the human brain and was capable of learning to recognize patterns and make simple decisions. Rosenblatt’s work laid the groundwork for modern neural networks and deep learning. His perceptron was initially implemented on a custom-built machine called the Mark I Perceptron, which used punched cards and was one of the earliest examples of machine learning hardware.