The perceptron and its limits
The logical neuron and Hebb's rule come together in the perceptron, the first network that learns from examples. Minsky and Papert later map its limits.
The McCulloch-Pitts neuron (December 1943)
McCulloch and Pitts describe the neuron as a logical threshold unit. Its connections are fixed, and the network does not learn.
Hebb's rule (1949)
Meanwhile, in psychology, Hebb proposes that the connection between two neurons grows stronger when one repeatedly helps make the other fire.
SNARC (1951)
Minsky and Edmonds build the SNARC, which strengthens the connections that have just acted whenever it receives a reward.
The perceptron (1957)
Rosenblatt starts from the McCulloch-Pitts neuron and Hebb's rule and builds the perceptron, which adjusts its weights every time it makes a mistake.
Perceptrons (1969)
Minsky and Papert prove what a perceptron with one adjustable layer cannot compute. For years they are blamed for the decline of neural network research, a reading that is disputed.