Pattern Recognition and Machine Learning (Information Science and Statistics)
Citations
14,635 citations
Cites background from "Pattern Recognition and Machine Lea..."
...To address overfitting, instead of depending on pre-wired regularizers and hyper-parameters (Bishop, 2006; Hertz, Krogh, & Palmer, 1991), self-delimiting RNNs (SLIM NNs) with competing units (Schmidhuber, 2012) can in principle learn to select their own runtime and their own numbers of effective…...
[...]
...…ExpectationMaximization (EM) (Dempster, Laird, & Rubin, 1977; Friedman, Hastie, & Tibshirani, 2001), e.g., Baldi and Chauvin (1996), Bengio (1991), Bishop (2006), Bottou (1991), Bourlard andMorgan (1994), Dahl, Yu, Deng, and Acero (2012), Hastie, Tibshirani, and Friedman (2009), Hinton, Deng, et…...
[...]
9,803 citations
4,960 citations
2,391 citations
Cites background from "Pattern Recognition and Machine Lea..."
...In contrast, non-parametric methods expand representational power in relation to collected data and, hence, are not limited by the representation power of a chosen parametrization (Bishop, 2006)....
[...]
2,291 citations
Cites background or methods from "Pattern Recognition and Machine Lea..."
...Statistical machine learning research has addressed some of these challenges by developing the field of probabilistic modeling, a field that provides an elegant approach to developing new methods for analyzing data (Pearl, 1988; Jordan, 1999; Bishop, 2006; Koller and Friedman, 2009; Murphy, 2012)....
[...]
...Further, the optimal mean-field distribution, without regard to its particular functional form, has factors in these families (Bishop, 2006)....
[...]