Machine Learning: A Bayesian and Optimization Perspective

2015

587 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/aaa76e15235d937d093a7063c0be86ed84494dee

Citations in the corpus

Learning the Number of Neurons in Deep Networks (2016, background): “While group sparsity lets us effectively remove some of the neurons, exploiting standard regularizers on the individual parameters has proven effective in the past for generalization purpose [Bartlett, 1996, Krogh and Hertz, 1992, Theodoridis, 2015, Collins and Kohli, 2014].”
FedLoc: Federated Learning Framework for Data-Driven Cooperative Localization and Location Data Processing (2020, methodology): “used by gradient vanishing or explosion. In the following, we brieﬂy review the batch gradient descent method for DNN training. More details about DNN and gradient descent type method can be found in [44, 45]. In general, the iterative training procedure follows three steps: 1)Randomly choose a set ”
On the influence of momentum acceleration on online learning (2016, methodology): “If the probability distribution of the data, θ, is known beforehand, then one can evaluate J(w) and seek its minimizer by means of a variety of gradient-descent or Newton-type methods (Polyak, 1987; Bertsekas, 1999; Nesterov, 2004).”
Nonparametric Bayesian Deep Networks with Local Competition (2018, methodology): “By using it as a prior, it allows for inferring how many components are needed for modeling a given set of observations, in a way that ensures sparsity in the obtained representations (Theodoridis, 2015).”
From Data Acquisition to Data Fusion: A Comprehensive Review and a Roadmap for the Identification of Activities of Daily Living Using Mobile Devices (2016, methodology): “In [26], data acquired with these sensors are fused with a combined algorithm, composed of Fisher’s discriminant ratio criterion and the J3 criterion for feature selection [97].”
A Unifying Review of Deep and Shallow Anomaly Detection (2020, methodology): “Our last modeling dimension D5 describes the Inference Mode, specifically whether a method performs Bayesian inference [416].”