Unsupervised learning: Difference between revisions

Content deleted Content added
Networks: Adding wikilinks
History: Adding wikilinks, spelling/grammar/punctuation/typographical correction
Line 45:
{| class="wikitable"
|-
| 1969 || [[Perceptrons (book)|Perceptrons]] by Minsky & Papert shows a [[perceptron]] without hidden layers fails on [[XOR]]
|-
| 1970s || (approximate dates) First [[AI winter]]
|-
| 1974 || Ising magnetic model proposed by {{ill|William A. Little (physicist)|lt=WA Little|de|William A. Little}} for cognition
|-
| 1980 || Fukushima introduces the [[neocognitron]], which is later called a convolution[[convolutional neural network]]. It is mostly used in SL, but deserves a mention here.
|-
| 1982 || Ising variant Hopfield net described as [[Content-addressable_memory|CAMs]] and classifiers by John Hopfield.
Line 57:
| 1983 || Ising variant Boltzmann machine with probabilistic neurons described by [[Geoffrey Hinton|Hinton]] & [[Terry Sejnowski|Sejnowski]] following Sherington & Kirkpatrick's 1975 work.
|-
| 1986 || [[Paul Smolensky]] publishes Harmony Theory, which is an RBM with practically the same Boltzmann energy function. Smolensky did not give a practical training scheme. Hinton did in mid-2000s.
|-
| 1995 || Schmidthuber introduces the [[Long_short-term_memory|LSTM]] neuron for languages.