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
30 Jun 2013
TL;DR: The book builds on the ideas put forward by the European research Cluster on the Internet of Things Strategic Research Agenda and presents global views and state of the art results on the challenges facing the research, development and deployment of IoT at the global level.
Abstract: The book aims to provide a broad overview of various topics of the Internet of Things (IoT) from the research and development priorities to enabling technologies, architecture, security, privacy, interoperability and industrial applications. It is intended to be a standalone book in a series that covers the Internet of Things activities of the IERC ? Internet of Things European Research Cluster from technology to international cooperation and the global "state of play". The book builds on the ideas put forward by the European research Cluster on the Internet of Things Strategic Research Agenda and presents global views and state of the art results on the challenges facing the research, development and deployment of IoT at the global level.
767 citations
TL;DR: A new notion of unfairness, disparate mistreatment, is introduced, defined in terms of misclassification rates, which is proposed for decision boundary-based classifiers and can be easily incorporated into their formulation as convex-concave constraints.
Abstract: Automated data-driven decision making systems are increasingly being used to assist, or even replace humans in many settings. These systems function by learning from historical decisions, often taken by humans. In order to maximize the utility of these systems (or, classifiers), their training involves minimizing the errors (or, misclassifications) over the given historical data. However, it is quite possible that the optimally trained classifier makes decisions for people belonging to different social groups with different misclassification rates (e.g., misclassification rates for females are higher than for males), thereby placing these groups at an unfair disadvantage. To account for and avoid such unfairness, in this paper, we introduce a new notion of unfairness, disparate mistreatment, which is defined in terms of misclassification rates. We then propose intuitive measures of disparate mistreatment for decision boundary-based classifiers, which can be easily incorporated into their formulation as convex-concave constraints. Experiments on synthetic as well as real world datasets show that our methodology is effective at avoiding disparate mistreatment, often at a small cost in terms of accuracy.
747 citations
Additional excerpts
...p(x|z = 0, y = 1) = N([1, 2], [5, 2; 2, 5]) p(x|z = 1, y = 1) = N([2, 3], [10, 1; 1, 4]) p(x|z = 0, y = −1) = N([0,−1], [7, 1; 1, 7]) p(x|z = 1, y = −1) = N([−5, 0], [5, 1; 1, 5])...
[...]
...15 for a logistic regression classifier [5]....
[...]
...p(x|z = 0, y = 1) = N([2, 0], [5, 1; 1, 5]) p(x|z = 1, y = 1) = N([2, 3], [5, 1; 1, 5]) p(x|z = 0, y = −1) = N([−1,−3], [5, 1; 1, 5]) p(x|z = 1, y = −1) = N([−1, 0], [5, 1; 1, 5])...
[...]
TL;DR: In this article, the authors present an overview of available machine learning techniques and structuring this rather complicated area, and a special focus is laid on the potential benefit and examples of successful applications in a manufacturing environment.
Abstract: The nature of manufacturing systems faces ever more complex, dynamic and at times even chaotic behaviors. In order to being able to satisfy the demand for high-quality products in an efficient manner, it is essential to utilize all means available. One area, which saw fast pace developments in terms of not only promising results but also usability, is machine learning. Promising an answer to many of the old and new challenges of manufacturing, machine learning is widely discussed by researchers and practitioners alike. However, the field is very broad and even confusing which presents a challenge and a barrier hindering wide application. Here, this paper contributes in presenting an overview of available machine learning techniques and structuring this rather complicated area. A special focus is laid on the potential benefit, and examples of successful applications in a manufacturing environment.
745 citations
Cites background from "Pattern Recognition and Machine Lea..."
...Additionally, it has to be kept in mind, that the different algorithms can be combined to maximize the classification power (Bishop, 2006)....
[...]
...that the different algorithms can be combined to maximize the classification power (Bishop, 2006)....
[...]
01 Jan 2010
TL;DR: A new approach to speaker verification is described which is based on a generative model of speaker and channel effects but differs from Joint Factor Analysis in several respects, including each utterance is represented by a low dimensional feature vector rather than by a high dimensional set of Baum-Welch statistics.
Abstract: We describe a new approach to speaker verification which, like Joint Factor Analysis, is based on a generative model of speaker and channel effects but differs from Joint Factor Analysis in several respects. Firstly, each utterance is represented by a low dimensional feature vector, rather than by a high dimensional set of Baum-Welch statistics. Secondly, heavy-tailed distributions are used in place of Gaussian distributions in formulating the model, so that the effect of outlying data is diminished, both in training the model and at recognition time. Thirdly, the likelihood ratio used for making verification decisions is calculated (using variational Bayes) in a way which is fully consistent with the modeling assumptions and the rules of probability. Finally, experimental results show that, in the case of telephone speech, these likelihood ratios do not need to be normalized in order to set a trial-independent threshold for verification decisions. We report results on female speakers for several conditions in the NIST 2008 speaker recognition evaluation data, including microphone as well as telephone speech. As measured both by equal error rates and the minimum values of the NIST detection cost function, the results on telephone speech are about 30% better than we have achieved using Joint Factor Analysis.
734 citations
Cites background or methods from "Pattern Recognition and Machine Lea..."
...where the expectation is taken with respect to h, thenL ≤ lnP (D) with equality holding iffQ(h) is the exact posterior P (h|D) [7]....
[...]
...This complication can be avoided by assuming a variational approximation of the form lnP (x1, x2|D) ≈ lnQ(x1) + lnQ(x2) and iteratively applying the standard variational Bayes update formulas [7] lnQ(x2) ≡ Ex1 [lnP (D,x1, x2)] lnQ(x1) ≡ Ex2 [lnP (D,x1, x2)] ....
[...]
...See the section on Bayesian PCA in [7]....
[...]
...(The Student’s t distribution is defined in the Appendix; see also [7]....
[...]
...s L1(s); this is the auxiliary function in Bishop’s formulation of the EM algorithm [7]....
[...]
TL;DR: This paper shows that formulating the problem in a naive Bayesian classification framework makes such preprocessing unnecessary and produces an algorithm that is simple, efficient, and robust, and it scales well as the number of classes grows.
Abstract: While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle perspective distortion. In this paper, we show that formulating the problem in a naive Bayesian classification framework makes such preprocessing unnecessary and produces an algorithm that is simple, efficient, and robust. Furthermore, it scales well as the number of classes grows. To recognize the patches surrounding keypoints, our classifier uses hundreds of simple binary features and models class posterior probabilities. We make the problem computationally tractable by assuming independence between arbitrary sets of features. Even though this is not strictly true, we demonstrate that our classifier nevertheless performs remarkably well on image data sets containing very significant perspective changes.
726 citations
Cites background from "Pattern Recognition and Machine Lea..."
...where Nr represents a regularization term, which behaves as a uniform Dirichlet prior [4] over feature values....
[...]