Artificial intelligence

The term artificial intelligence was first used by John McCarthy in 1956. The goals of AI research include reasoning, knowledge representation, planning, learning, natural language processing, perception and the ability to move and manipulate objects.
Machine learning (ML) is a sub-field of AI. The name machine learning was used in 1959 by Arthur Samuel. ML uses statistical techniques to give computer systems the ability to "learn" from data, without being explicitly programmed.
Deep learning is a specific subfield of machine learning. The term Deep Learning was introduced by Rina Dechter in 1986. Deep learning is a class of machine learning algorithms such as: cascades of multiple layers of nonlinear processing units for feature extraction and transformation; learning in supervised and/or unsupervised manner; learning multiple levels of representations.

History

date

inventor

invention

1943

Warren McCulloch and Walter Pitts

threshold logic

1949

D. O. Hebb

Hebbian learning

1954

Farley and Clark

Hebbian network simulator

1958

Rosenblatt

perceptron

1965

Ivakhnenko and Lapa

Group Method of Data Handling

1975

Werbos

backpropagation algorithm

1988

Yann LeCun

Convolutional Neural Network

2006

Hinton

restricted Boltzmann machine

2011

Ciresan, D. C.; Meier, U.; Masci, J.; Gambardella, L. M.; Schmidhube

Convolutional Neural Networks for Image Classification

Variants

name

Group method of data handling (GMDH)

Convolutional neural network (CNN)

Long short-term memory (LSTM)

Deep Reservoir Computing and Deep Echo State Networks (deepESNs)

Deep belief network (DBN)

Large memory storage and retrieval neural networks (LAMSTAR)

Stacked auto-encoders

Deep stacking network (DSN)

Tensor deep stacking networks

Spike-and-slab RBMs

Compound hierarchical-deep models

Deep predictive coding network (DPCN)