Pattern Recognition and Machine Learning
TL;DR: This book covers a broad range of topics for regular factorial designs and presents all of the material in very mathematical fashion and will surely become an invaluable resource for researchers and graduate students doing research in the design of factorial experiments.
Abstract: (2007). Pattern Recognition and Machine Learning. Technometrics: Vol. 49, No. 3, pp. 366-366.
Citations
More filters
Proceedings Article•
01 Jan 2014TL;DR: This work adopts a continuous and passive authentication mechanism based on a user’s touch operations on the touchscreen that is suitable for smartphones, as it requires no extra hardware or intrusive user interface.
Abstract: Current smartphones generally cannot continuously authenticate users during runtime. This poses severe security and privacy threats: A malicious user can manipulate the phone if bypassing the screen lock. To solve this problem, our work adopts a continuous and passive authentication mechanism based on a user’s touch operations on the touchscreen. Such a mechanism is suitable for smartphones, as it requires no extra hardware or intrusive user interface. We study how to model multiple types of touch data and perform continuous authentication accordingly. As a first attempt, we also investigate the fundamentals of touch operations as biometrics by justifying their distinctiveness and permanence. A onemonth experiment is conducted involving over 30 users. Our experiment results verify that touch biometrics can serve as a promising method for continuous and passive authentication.
195 citations
Cites background or methods from "Pattern Recognition and Machine Lea..."
...This is not surprising: As the number increases, the attacker samples are getting more diverse, and the SVM will suffer overfitting to the attacker class....
[...]
...We adopt a state-of-the-art statistics-based classification method, i.e., the Support Vector Machine (SVM) [6]....
[...]
...Finally, note that SVM is not the only option of classifier for our user authentication approach....
[...]
...We adopt SVM since it has long been proven successful in many classification applications....
[...]
...Since our approach heavily relies on the SVM classifier, we tune the SVM parameters to get the EER....
[...]
TL;DR: Investigation of various Bayesian ANN architectures for predicting phenotypes in two data sets consisting of milk production in Jersey cows and yield of inbred lines of wheat suggests that neural networks may be useful for predicting complex traits using high-dimensional genomic information, a situation where the number of unknowns exceeds sample size.
Abstract: Background
In the study of associations between genomic data and complex phenotypes there may be relationships that are not amenable to parametric statistical modeling. Such associations have been investigated mainly using single-marker and Bayesian linear regression models that differ in their distributions, but that assume additive inheritance while ignoring interactions and non-linearity. When interactions have been included in the model, their effects have entered linearly. There is a growing interest in non-parametric methods for predicting quantitative traits based on reproducing kernel Hilbert spaces regressions on markers and radial basis functions. Artificial neural networks (ANN) provide an alternative, because these act as universal approximators of complex functions and can capture non-linear relationships between predictors and responses, with the interplay among variables learned adaptively. ANNs are interesting candidates for analysis of traits affected by cryptic forms of gene action.
195 citations
Cites background or methods from "Pattern Recognition and Machine Lea..."
...A natural way of attaining this compromise between goodness of fit and predictive ability is by means of Bayesian methods [2,11,15,18]....
[...]
...Hence, it seems clear, at least for wheat yield in this data set, that the non-parametric methods can outperform a strong learner, the Bayesian Lasso, and that the neural networks are competitive with the highly regarded support vector methods [11]....
[...]
...(ANN) provide an interesting alternative because these learning machines can act as universal approximators of complex functions [10,11]....
[...]
...The choice of number of neurons can be based on cross-validation, as in the present data, or on standard Bayesian metrics for model comparison [11,15]....
[...]
Proceedings Article•
14 Aug 2019TL;DR: In this article, the authors argue that results are commonly inflated due to two pervasive sources of experimental bias: spatial bias caused by distributions of training and testing data that are not representative of a real-world deployment.
Abstract: Is Android malware classification a solved problem? Published F1 scores of up to 0.99 appear to leave very little room for improvement. In this paper, we argue that results are commonly inflated due to two pervasive sources of experimental bias: "spatial bias" caused by distributions of training and testing data that are not representative of a real-world deployment; and "temporal bias" caused by incorrect time splits of training and testing sets, leading to impossible configurations. We propose a set of space and time constraints for experiment design that eliminates both sources of bias. We introduce a new metric that summarizes the expected robustness of a classifier in a real-world setting, and we present an algorithm to tune its performance. Finally, we demonstrate how this allows us to evaluate mitigation strategies for time decay such as active learning. We have implemented our solutions in TESSERACT, an open source evaluation framework for comparing malware classifiers in a realistic setting. We used TESSERACT to evaluate three Android malware classifiers from the literature on a dataset of 129K applications spanning over three years. Our evaluation confirms that earlier published results are biased, while also revealing counter-intuitive performance and showing that appropriate tuning can lead to significant improvements.
194 citations
11 Mar 2019
TL;DR: WiDeep combines a stacked denoising autoencoders deep learning model and a probabilistic framework to handle the noise in the received WiFi signal and capture the complex relationship between the WiFi APs signals heard by the mobile phone and its location.
Abstract: Robust and accurate indoor localization has been the goal of several research efforts over the past decade. Due to the ubiquitous availability of WiFi indoors, many indoor localization systems have been proposed relying on WiFi fingerprinting. However, due to the inherent noise and instability of the wireless signals, the localization accuracy usually degrades and is not robust to dynamic changes in the environment.We present WiDeep, a deep learning-based indoor localization system that achieves a fine-grained and robust accuracy in the presence of noise. Specifically, WiDeep combines a stacked denoising autoencoders deep learning model and a probabilistic framework to handle the noise in the received WiFi signal and capture the complex relationship between the WiFi APs signals heard by the mobile phone and its location. WiDeep also introduces a number of modules to address practical challenges such as avoiding over-training and handling heterogeneous devices.We evaluate WiDeep in two testbeds of different sizes and densities of access points. The results show that it can achieve a mean localization accuracy of 2.64m and 1.21m for the larger and the smaller testbeds, respectively. This accuracy outperforms the state-of-the-art techniques in all test scenarios and is robust to heterogeneous devices.
194 citations
Cites background from "Pattern Recognition and Machine Lea..."
...However, they usually assume that the signals from different access points are independent to avoid the curse of dimensionality problem [20]....
[...]
...Despite probabilistic techniques being able to handle the inherently noisy wireless signals in a better way than deterministic techniques, they usually assume that the signals from different APs are independent to avoid the curse of dimensionality problem [20]....
[...]
Posted Content•
TL;DR: Automatic differentiation variational inference (ADVI) as discussed by the authors automatically determines an appropriate variational family and optimizes the variational objective, which is a scalable technique for approximate Bayesian inference.
Abstract: Variational inference is a scalable technique for approximate Bayesian inference. Deriving variational inference algorithms requires tedious model-specific calculations; this makes it difficult to automate. We propose an automatic variational inference algorithm, automatic differentiation variational inference (ADVI). The user only provides a Bayesian model and a dataset; nothing else. We make no conjugacy assumptions and support a broad class of models. The algorithm automatically determines an appropriate variational family and optimizes the variational objective. We implement ADVI in Stan (code available now), a probabilistic programming framework. We compare ADVI to MCMC sampling across hierarchical generalized linear models, nonconjugate matrix factorization, and a mixture model. We train the mixture model on a quarter million images. With ADVI we can use variational inference on any model we write in Stan.
194 citations