http://colah.github.io/posts/2014-03-NN-Manifolds-Topology/ http://cs.stanford.edu/people/karpathy/convnetjs//demo/classify2d.html http://playground.tensorflow.org/#activation=tanh&batchSize=10&dataset=circle®Dataset=reg-plane&learningRate=0.03®ularizationRate=0&noise=0&networkShape=8,2&seed=0.49146&showTestData=false&discretize=false&percTrainData=50&x=true&y=true&xTimesY=true&xSquared=true&ySquared=true&cosX=false&sinX=true&cosY=false&sinY=true&collectStats=false&problem=classification&initZero=false&hideText=false http://colah.github.io/posts/2015-08-Backprop/
DARPA Helps Paralyzed Man Feel Again Using a Brain-Controlled Robotic Arm
中文版 OUTREACH@DARPA.MIL 10/13/2016 A DARPA-funded research team has demonstrated for the first time in a human a technology that allows an individual to experience the sensation of touch directly in the brain through a neural interface system connected to a
Deep Belief Network 深度信念网络
一直关注CNN 和RNN 对于早期的DBN略知一二,今天花了点时间看看了看看 说说我的看法 DBN可以看做深度学习的一个分水岭,它真正意义上解决了神经网络的训练方法,也使得深度学习能够深度下去。 你在CNN RNN SNN都可以看到它类似的身影 Hilton老爷子做的贡献是很大的,没有这个玩意,后续的各种变态很难说的