Results 1  10
of
162
An InformationTheoretic Definition of Similarity
 In Proceedings of the 15th International Conference on Machine Learning
, 1998
"... Similarity is an important and widely used concept. Previous definitions of similarity are tied to a particular application or a form of knowledge representation. We present an informationtheoretic definition of similarity that is applicable as long as there is a probabilistic model. We demonstrate ..."
Abstract

Cited by 769 (0 self)
 Add to MetaCart
Similarity is an important and widely used concept. Previous definitions of similarity are tied to a particular application or a form of knowledge representation. We present an informationtheoretic definition of similarity that is applicable as long as there is a probabilistic model. We demonstrate how our definition can be used to measure the similarity in a number of different domains.
The earth mover’s distance as a metric for image retrieval
 International Journal of Computer Vision
, 2000
"... 1 Introduction Multidimensional distributions are often used in computer vision to describe and summarize different features of an image. For example, the onedimensional distribution of image intensities describes the overall brightness content of a grayscale image, and a threedimensional distrib ..."
Abstract

Cited by 464 (4 self)
 Add to MetaCart
1 Introduction Multidimensional distributions are often used in computer vision to describe and summarize different features of an image. For example, the onedimensional distribution of image intensities describes the overall brightness content of a grayscale image, and a threedimensional distribution can play a similar role for color images. The texture content of an image can be described by a distribution of local signal energy over frequency. These descriptors can be used in a variety of applications including, for example, image retrieval.
Blind Signal Separation: Statistical Principles
, 2003
"... Blind signal separation (BSS) and independent component analysis (ICA) are emerging techniques of array processing and data analysis, aiming at recovering unobserved signals or `sources' from observed mixtures (typically, the output of an array of sensors), exploiting only the assumption of mutual i ..."
Abstract

Cited by 395 (4 self)
 Add to MetaCart
Blind signal separation (BSS) and independent component analysis (ICA) are emerging techniques of array processing and data analysis, aiming at recovering unobserved signals or `sources' from observed mixtures (typically, the output of an array of sensors), exploiting only the assumption of mutual independence between the signals. The weakness of the assumptions makes it a powerful approach but requires to venture beyond familiar second order statistics. The objective of this paper is to review some of the approaches that have been recently developed to address this exciting problem, to show how they stem from basic principles and how they relate to each other.
Markov Localization for Mobile Robots in Dynamic Environments
 Journal of Artificial Intelligence Research
, 1999
"... Localization, that is the estimation of a robot's location from sensor data, is a fundamental problem in mobile robotics. This papers presents a version of Markov localization which provides accurate position estimates and which is tailored towards dynamic environments. The key idea of Markov loc ..."
Abstract

Cited by 284 (46 self)
 Add to MetaCart
Localization, that is the estimation of a robot's location from sensor data, is a fundamental problem in mobile robotics. This papers presents a version of Markov localization which provides accurate position estimates and which is tailored towards dynamic environments. The key idea of Markov localization is to maintain a probability density over the space of all locations of a robot in its environment. Our approach represents this space metrically, using a negrained grid to approximate densities. It is able to globally localize the robot from scratch and to recover from localization failures. It is robust to approximate models of the environment (such as occupancy grid maps) and noisy sensors (such as ultrasound sensors). Our approach also includes a ltering technique which allows a mobile robot to reliably estimate its position even in densely populated environments in which crowds of people block the robot's sensors for extended periods of time. The method described he...
Learning with Labeled and Unlabeled Data
, 2001
"... In this paper, on the one hand, we aim to give a review on literature dealing with the problem of supervised learning aided by additional unlabeled data. On the other hand, being a part of the author's first year PhD report, the paper serves as a frame to bundle related work by the author as well as ..."
Abstract

Cited by 166 (3 self)
 Add to MetaCart
In this paper, on the one hand, we aim to give a review on literature dealing with the problem of supervised learning aided by additional unlabeled data. On the other hand, being a part of the author's first year PhD report, the paper serves as a frame to bundle related work by the author as well as numerous suggestions for potential future work. Therefore, this work contains more speculative and partly subjective material than the reader might expect from a literature review. We give a rigorous definition of the problem and relate it to supervised and unsupervised learning. The crucial role of prior knowledge is put forward, and we discuss the important notion of inputdependent regularization. We postulate a number of baseline methods, being algorithms or algorithmic schemes which can more or less straightforwardly be applied to the problem, without the need for genuinely new concepts. However, some of them might serve as basis for a genuine method. In the literature revi...
Infomax and Maximum Likelihood for Blind Source Separation
, 1997
"... Algorithms for the blind separation of sources can be derived from several different principles. This letter shows that the recently proposed infomax principle is equivalent to maximum likelihood. Introduction. Source separation consists in recovering a set of unobservable signals (sources) from a ..."
Abstract

Cited by 134 (2 self)
 Add to MetaCart
Algorithms for the blind separation of sources can be derived from several different principles. This letter shows that the recently proposed infomax principle is equivalent to maximum likelihood. Introduction. Source separation consists in recovering a set of unobservable signals (sources) from a set of observed mixtures. In its simplest form, a n \Theta 1 vector x of observations (typically, the output of n sensors) is modeled as x = A ? s (1) where the `mixing matrix' A ? is invertible and the n \Theta 1 vector s = [s 1 ; : : : ; s n ] T has independent components: its probability density function (p.d.f.) r(s) factors as r(s) = Y i=1;n r i (s i ) (2) where r i (s i ) is the p.d.f. of s i . 1 Based on these assumptions and on realizations of x, the aim is to estimate matrix A ? or, equivalently, to find a `separating matrix' B such that y = Bx = BA ? s is an estimate of the source signals. A guiding principle for source separation is to optimize a function OE(B) called ...
Pseudorandom generators without the XOR Lemma
, 1998
"... Madhu Sudan y Luca Trevisan z Salil Vadhan x Abstract Impagliazzo and Wigderson [IW97] have recently shown that if there exists a decision problem solvable in time 2 O(n) and having circuit complexity 2 n) (for all but finitely many n) then P = BPP. This result is a culmination of a serie ..."
Abstract

Cited by 130 (21 self)
 Add to MetaCart
Madhu Sudan y Luca Trevisan z Salil Vadhan x Abstract Impagliazzo and Wigderson [IW97] have recently shown that if there exists a decision problem solvable in time 2 O(n) and having circuit complexity 2 n) (for all but finitely many n) then P = BPP. This result is a culmination of a series of works showing connections between the existence of hard predicates and the existence of good pseudorandom generators. The construction of Impagliazzo and Wigderson goes through three phases of "hardness amplification" (a multivariate polynomial encoding, a first derandomized XOR Lemma, and a second derandomized XOR Lemma) that are composed with the Nisan Wigderson [NW94] generator. In this paper we present two different approaches to proving the main result of Impagliazzo and Wigderson. In developing each approach, we introduce new techniques and prove new results that could be useful in future improvements and/or applications of hardnessrandomness tradeoffs. Our first result is that when (a modified version of) the NisanWigderson generator construction is applied with a "mildly" hard predicate, the result is a generator that produces a distribution indistinguishable from having large minentropy. An extractor can then be used to produce a distribution computationally indistinguishable from uniform. This is the first construction of a pseudorandom generator that works with a mildly hard predicate without doing hardness amplification. We then show that in the ImpagliazzoWigderson construction only the first hardnessamplification phase (encoding with multivariate polynomial) is necessary, since it already gives the required averagecase hardness. We prove this result by (i) establishing a connection between the hardnessamplification problem and a listdecoding...
Texture Mixing and Texture Movie Synthesis using Statistical Learning
 IEEE Transactions on Visualization and Computer Graphics
, 2001
"... We present an algorithm based on statistical learning for synthesizing static and timevarying textures matching the appearance of an input texture. Our algorithm is general and automatic, and it works well on various types of textures including 1D sound textures, 2D texture images and 3D texture mo ..."
Abstract

Cited by 109 (7 self)
 Add to MetaCart
We present an algorithm based on statistical learning for synthesizing static and timevarying textures matching the appearance of an input texture. Our algorithm is general and automatic, and it works well on various types of textures including 1D sound textures, 2D texture images and 3D texture movies. The same method is also used to generate 2D texture mixtures that simultaneously capture the appearance of a number of different input textures. In our approach, input textures are treated as sample signals generated by a stochastic process. We first construct a tree representing a hierarchical multiscale transform of the signal using wavelets. From this tree, new random trees are generated by learning and sampling the conditional probabilities of the paths in the original tree. Transformation of these random trees back into signals results in new random textures. In the case of 2D texture synthesis our algorithm produces results that are generally as good or better than those produce...
Energyefficient scheduling of packet transmissions over wireless networks
 in Proc. INFOCOM Conf
"... Abstract—The paper develops algorithms for minimizing the energy required to transmit packets in a wireless environment. It is motivated by the following observation: In many channel coding schemes it is possible to significantly lower the transmission energy by transmitting packets over a long peri ..."
Abstract

Cited by 99 (3 self)
 Add to MetaCart
Abstract—The paper develops algorithms for minimizing the energy required to transmit packets in a wireless environment. It is motivated by the following observation: In many channel coding schemes it is possible to significantly lower the transmission energy by transmitting packets over a long period of time. Based on this observation, we show that for a variety of scenarios the offline energyefficient transmission scheduling problem reduces to a convex optimization problem. Unlike for the special case of a single transmitterreceiver pair studied in [5], the problem does not, in general, admit a closedform solution when there are multiple users. By exploiting the special structure of the problem, however, we are able to devise energyefficient transmission schedules. For the downlink channel, with a single transmitter and multiple receivers, we devise an iterative algorithm, called MoveRight, that yields the optimal offline schedule. The MoveRight algorithm also optimally solves the downlink problem with additional constraints imposed by
Object recognition with informative features and linear classification
 In ICCV
, 2003
"... In this paper we show that efficient object recognition can be obtained by combining informative features with linear classification. The results demonstrate the superiority of informative classspecific features, as compared with generic type features such as wavelets, for the task of object recogn ..."
Abstract

Cited by 99 (4 self)
 Add to MetaCart
In this paper we show that efficient object recognition can be obtained by combining informative features with linear classification. The results demonstrate the superiority of informative classspecific features, as compared with generic type features such as wavelets, for the task of object recognition. We show that information rich features can reach optimal performance with simple linear separation rules, while generic feature based classifiers require more complex classification schemes. This is significant because efficient and optimal methods have been developed for spaces that allow linear separation. To compare different strategies for feature extraction, we trained and compared classifiers working in feature spaces of the same low dimensionality, using two feature types (image fragments vs. wavelets) and two classification rules (linear hyperplane and a Bayesian Network). The results show that by maximizing the individual information of the features, it is possible to obtain efficient classification by a simple linear separating rule, as well as more efficient learning. 1.