Changes

[https://en.wikipedia.org/wiki/Convolutional_neural_network Convolutional neural networks] (CNN) form a subclass of feedforward neural networks that have special weight constraints, individual neurons are tiled in such a way that they respond to overlapping regions. A neuron of a convolutional layer is connected to a correspondent [https://en.wikipedia.org/wiki/Receptive_field receptive field] of the previous layer, a small subset of their neurons. A distinguishing feature of CNNs is that many neurons share the same bias and vector of weights, dubbed filter. This reduces [[Memory#Footprint|memory footprint]] because a single bias and a single vector of weights is used across all receptive fields sharing that filter, rather than each receptive field having its own bias and vector of weights. Convolutional NNs are suited for deep learning and are highly suitable for parallelization on [[GPU|GPUs]] <ref>[http://parse.ele.tue.nl/education/cluster2 PARsE | Education | GPU Cluster | Efficient mapping of the training of Convolutional Neural Networks to a CUDA-based cluster]</ref>. They were [[Go#CNN|research topic]] in the game of [[Go]] since 2008 <ref>[[Ilya Sutskever]], [[Vinod Nair]] ('''2008'''). ''Mimicking Go Experts with Convolutional Neural Networks''. [http://dblp.uni-trier.de/db/conf/icann/icann2008-2.html#SutskeverN08 ICANN 2008], [http://www.cs.utoronto.ca/~ilya/pubs/2008/go_paper.pdf pdf]</ref>, and along with the [[Neural Networks#Residual|residual]] modification successful applied in [[Go]] and other [[Games|games]], most spectacular due to [[AlphaGo]] in 2015 and [[AlphaZero]] in 2017.