Deep learning
Citations
520 citations
518 citations
Cites background or methods from "Deep learning"
...Current deep learning stochastic gradient algorithms instead use parameter updates based on gradient averages over small subsets of the full training set, or mini-batches, and the term batch size is commonly used to refer to the size of a mini-batch (Goodfellow et al., 2016)....
[...]
...The use of deep neural networks has recently enabled significant advances in a number of applications, including computer vision, speech recognition and natural language processing, and in reinforcement learning for robotic control and game playing (LeCun et al., 2015; Schmidhuber, 2015; Goodfellow et al., 2016; Arulkumaran et al., 2017)....
[...]
...…enabled significant advances in a number of applications, including computer vision, speech recognition and natural language processing, and in reinforcement learning for robotic control and game playing (LeCun et al., 2015; Schmidhuber, 2015; Goodfellow et al., 2016; Arulkumaran et al., 2017)....
[...]
...Deep learning optimization is typically based on Stochastic Gradient Descent (SGD) or one of its variants (Bottou et al., 2016; Goodfellow et al., 2016)....
[...]
518 citations
517 citations
Additional excerpts
...Memory(LSTM), CNN(Convolutional Neural Network) etc [9]....
[...]
517 citations
References
72,897 citations
42,067 citations
23,814 citations
23,074 citations
16,717 citations