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
TL;DR: The article deals with the analysis and interpretation of dynamic scenes typical of urban driving, to assess risks of collision for the ego-vehicle with the use of Hidden Markov Models and Gaussian processes.
Abstract: The article deals with the analysis and interpretation of dynamic scenes typical of urban driving. The key objective is to assess risks of collision for the ego-vehicle. We describe our concept and methods, which we have integrated and tested on our experimental platform on a Lexus car and a driving simulator. The on-board sensors deliver visual, telemetric and inertial data for environment monitoring. The sensor fusion uses our Bayesian Occupancy Filter for a spatio-temporal grid representation of the traffic scene. The underlying probabilistic approach is capable of dealing with uncertainties when modeling the environment as well as detecting and tracking dynamic objects. The collision risks are estimated as stochastic variables and are predicted for a short period ahead with the use of Hidden Markov Models and Gaussian processes. The software implementation takes advantage of our methods, which allow for parallel computation. Our tests have proven the relevance and feasibility of our approach for improving the safety of car driving.
316 citations
Cites methods from "Pattern Recognition and Machine Lea..."
...Because the number Nk is known from the prediction step, we apply a K-means based algorithm [48]....
[...]
TL;DR: The segmented and annotated IAPR TC-12 benchmark is introduced; an extended resource for the evaluation of AIA methods as well as the analysis of their impact on multimedia information retrieval.
315 citations
Cites background from "Pattern Recognition and Machine Lea..."
...One of the main challenges in OVA classification is choosing a way to combine the outputs of binary classifiers such that errors with respect to unseen data are minimized [39]....
[...]
Posted Content•
TL;DR: Linear dimensionality reduction methods have been developed with a variety of names and motivations in many fields, and perhaps as a result the connections between all these methods have not been highlighted as discussed by the authors.
Abstract: Linear dimensionality reduction methods are a cornerstone of analyzing high dimensional data, due to their simple geometric interpretations and typically attractive computational properties. These methods capture many data features of interest, such as covariance, dynamical structure, correlation between data sets, input-output relationships, and margin between data classes. Methods have been developed with a variety of names and motivations in many fields, and perhaps as a result the connections between all these methods have not been highlighted. Here we survey methods from this disparate literature as optimization programs over matrix manifolds. We discuss principal component analysis, factor analysis, linear multidimensional scaling, Fisher's linear discriminant analysis, canonical correlations analysis, maximum autocorrelation factors, slow feature analysis, sufficient dimensionality reduction, undercomplete independent component analysis, linear regression, distance metric learning, and more. This optimization framework gives insight to some rarely discussed shortcomings of well-known methods, such as the suboptimality of certain eigenvector solutions. Modern techniques for optimization over matrix manifolds enable a generic linear dimensionality reduction solver, which accepts as input data and an objective to be optimized, and returns, as output, an optimal low-dimensional projection of the data. This simple optimization framework further allows straightforward generalizations and novel variants of classical methods, which we demonstrate here by creating an orthogonal-projection canonical correlations analysis. More broadly, this survey and generic solver suggest that linear dimensionality reduction can move toward becoming a blackbox, objective-agnostic numerical technology.
313 citations
04 Jun 2009
TL;DR: A scalable face matching algorithm capable of dealing with faces subject to several concurrent and uncontrolled factors, such as variations in pose, expression, illumination, resolution, as well as scale and misalignment problems, is proposed.
Abstract: We propose a scalable face matching algorithm capable of dealing with faces subject to several concurrent and uncontrolled factors, such as variations in pose, expression, illumination, resolution, as well as scale and misalignment problems. Each face is described in terms of multi-region probabilistic histograms of visual words, followed by a normalised distance calculation between the histograms of two faces. We also propose a fast histogram approximation method which dramatically reduces the computational burden with minimal impact on discrimination performance. Experiments on the "Labeled Faces in the Wild" dataset (unconstrained environments) as well as FERET (controlled variations) show that the proposed algorithm obtains performance on par with a more complex method and displays a clear advantage over predecessor systems. Furthermore, the use of multiple regions (as opposed to a single overall region) improves accuracy in most cases, especially when dealing with illumination changes and very low resolution images. The experiments also show that normalised distances can noticeably improve robustness by partially counteracting the effects of image variations.
313 citations
Cites methods from "Pattern Recognition and Machine Lea..."
...In the first part, the gaussians from the visual dictionary model are placed into K clusters via the k-means algorithm [8]....
[...]
...The visual dictionary is obtained by pooling a large number of feature vectors from training faces, followed by employing the Expectation Maximisation algorithm [8] to optimise the dictionary’s parameters (i....
[...]
...The visual dictionary model employed here is a convex mixture of gaussians [8], parameterised by...
[...]
...While both MRH and RBT use image patches for analysis, RBT also uses: (i) quantised differences, via ‘extremely-randomised trees’, between corresponding patches, (ii) a cross-correlation based search to determine patch correspondence, and (iii) an SVM classifier [8] for final classification....
[...]
01 Dec 2008
TL;DR: This work obtains a more natural form of LQG duality by replacing the Kalman-Bucy filter with the information filter and generalizes this result to non-linear stochastic systems, discrete stochastics systems, and deterministic systems.
Abstract: Optimal control and estimation are dual in the LQG setting, as Kalman discovered, however this duality has proven difficult to extend beyond LQG. Here we obtain a more natural form of LQG duality by replacing the Kalman-Bucy filter with the information filter. We then generalize this result to non-linear stochastic systems, discrete stochastic systems, and deterministic systems. All forms of duality are established by relating exponentiated costs to probabilities. Unlike the LQG setting where control and estimation are in one-to-one correspondence, in the general case control turns out to be a larger problem class than estimation and only a sub-class of control problems have estimation duals. These are problems where the Bellman equation is intrinsically linear. Apart from their theoretical significance, our results make it possible to apply estimation algorithms to control problems and vice versa.
312 citations
Cites background from "Pattern Recognition and Machine Lea..."
...Other popular Bayesian inference algorithms include variational approximations and loopy belief propagation in graphical models [2], although these algorithms are usually applied to discrete state spaces....
[...]