#neural-networks
7 events tagged with this keyword
McCulloch-Pitts Neuron Model
Warren McCulloch and Walter Pitts propose the first mathematical neuron model, laying the theoretical foundation for neural networks.
Perceptron: First Neural Computer
Frank Rosenblatt invents the Perceptron Mark I, the first hardware implementation based on neural network principles.
Perceptrons and the AI Winter
Minsky and Papert publish "Perceptrons", highlighting the limitations of single-layer neural networks, leading to the first decline in neural network research.
Backpropagation Algorithm Revival
Rumelbart, Hinton, and Williams popularize the backpropagation algorithm, reviving neural network research.
LSTM Neural Network
Hochreiter and Schmidhuber propose LSTM, solving the long-term dependency problem of recurrent neural networks.
Deep Belief Network: Deep Learning Revival
Geoffrey Hinton proposes Deep Belief Networks, pioneering effective methods for training deep learning.
Dropout Regularization
Geoffrey Hinton and colleagues propose Dropout technique, effectively preventing neural network overfitting.