Breakout google
A breakout is typically characterized by two steady states and an intermediate transition period. Broadly speaking, breakouts have two flavors:
1. Mean shift: A sudden jump in the time series corresponds to a mean shift. A sudden jump in CPU utilization from 40% to 60% would exemplify a mean shift.
2. Ramp up: A gradual increase in the value of the metric from one steady state to another constitutes a ramp up. A gradual increase in CPU utilization from 40% to 60% would exemplify a ramp up. …


Max-Margin Deep Generative Models (mmDGMs) google
Deep generative models (DGMs) are effective on learning multilayered representations of complex data and performing inference of input data by exploring the generative ability. However, it is relatively insufficient to empower the discriminative ability of DGMs on making accurate predictions. This paper presents max-margin deep generative models (mmDGMs) and a class-conditional variant (mmDCGMs), which explore the strongly discriminative principle of max-margin learning to improve the predictive performance of DGMs in both supervised and semi-supervised learning, while retaining the generative capability. In semi-supervised learning, we use the predictions of a max-margin classifier as the missing labels instead of performing full posterior inference for efficiency; we also introduce additional max-margin and label-balance regularization terms of unlabeled data for effectiveness. We develop an efficient doubly stochastic subgradient algorithm for the piecewise linear objectives in different settings. Empirical results on various datasets demonstrate that: (1) max-margin learning can significantly improve the prediction performance of DGMs and meanwhile retain the generative ability; (2) in supervised learning, mmDGMs are competitive to the best fully discriminative networks when employing convolutional neural networks as the generative and recognition models; and (3) in semi-supervised learning, mmDCGMs can perform efficient inference and achieve state-of-the-art classification results on several benchmarks. …

Mixture Density Network google
The core idea is to have a Neural Net that predicts an entire (and possibly complex) distribution. In this example we’re predicting a mixture of gaussians distributions via its sufficient statistic. This means that the network knows what it doesn’t know: it will predict diffuse distributions in situations where the target variable is very noisy, and it will predict a much more peaky distribution in nearly deterministic parts. …

Advertisements