We propose a new model for natural image statistics. Instead of minimizing dependency between components of natural images, we maximize a simple form of dependency in the form of tree-dependencies. By learning filters...
详细信息
ISBN:
(纸本)9781615679119
We propose a new model for natural image statistics. Instead of minimizing dependency between components of natural images, we maximize a simple form of dependency in the form of tree-dependencies. By learning filters and tree structures which are best suited for natural images we observe that the resulting filters are edge filters, similar to the famous ICA on natural images results. Calculating the likelihood of an image patch using our model requires estimating the squared output of pairs of filters connected in the tree. We observe that after learning, these pairs of filters are predominantly of similar orientations but different phases, so their joint energy resembles models of complex cells.
We propose a new model for natural image statistics. Instead of minimizing dependency between components of natural images, we maximize a simple form of dependency in the form of tree-dependencies. By learning filters...
ISBN:
(纸本)9781615679119
We propose a new model for natural image statistics. Instead of minimizing dependency between components of natural images, we maximize a simple form of dependency in the form of tree-dependencies. By learning filters and tree structures which are best suited for natural images we observe that the resulting filters are edge filters, similar to the famous ICA on natural images results. Calculating the likelihood of an image patch using our model requires estimating the squared output of pairs of filters connected in the tree. We observe that after learning, these pairs of filters are predominantly of similar orientations but different phases, so their joint energy resembles models of complex cells.
Loss of alertness can have dire consequences for people controlling motorized equipment or for people in professions such as defense. Electroencephalogram (EEG) is known to be related to alertness of the person, but d...
详细信息
Loss of alertness can have dire consequences for people controlling motorized equipment or for people in professions such as defense. Electroencephalogram (EEG) is known to be related to alertness of the person, but due to high level of noise and low signal strength, the use of EEG for such applications has been considered to be unreliable. This study reports the fractal analysis of EEG and identifies the use of maximum fractal length (MFL) as a feature that is inversely correlated with the alertness of the subject. The results show that MFL (of only single channel of EEG) indicates the loss of alertness of the individual with mean (inverse) correlation coefficient = 3D 0.82.
Changes of ICP waveform morphology are characterized with different patients' states like hypertension, hydrocephalus and traumatic brain injury etc. Morphological clustering and analysis of ICP pulse (MOCAIP) app...
详细信息
Changes of ICP waveform morphology are characterized with different patients' states like hypertension, hydrocephalus and traumatic brain injury etc. Morphological clustering and analysis of ICP pulse (MOCAIP) approach is recently developed to extract ICP morphology feature, in which hierarchical clustering is used to extract the dominated pulse. In this paper, we evaluate the feasibility of using principle component analysis (PCA) and independent component analysis (ICA) to extract dominated pulse. The comparative study among clustering, PCA and ICP based approaches shows that PCA approach may be an alternative of clustering approach to extract dominated pulse in a faster fashion when dataset is of large size.
Relevance can be identified with an extension of the classical notion of minimal sufficient statistics. Can be quantified using information theoretic notions, leading to the IB principle. Yielding practical algorithms...
We derive a generalization bound for multiclassification schemes based on grid clustering in categorical parameter product spaces. Grid clustering partitions the parameter space in the form of a Cartesian product of p...
详细信息
ISBN:
(纸本)9781605582054
We derive a generalization bound for multiclassification schemes based on grid clustering in categorical parameter product spaces. Grid clustering partitions the parameter space in the form of a Cartesian product of partitions for each of the parameters. The derived bound provides a means to evaluate clustering solutions in terms of the generalization power of a built-on classifier. For classification based on a single feature the bound serves to find a globally optimal classification rule. Comparison of the generalization power of individual features can then be used for feature ranking. Our experiments show that in this role the bound is much more precise than mutual information or normalized correlation indices. Copyright 2008 by the author(s)/owner(s).
Over the past few years, the notion of stability in data clustering has received growing attention as a cluster validation criterion in a sample-based framework. However, recent work has shown that as the sample size ...
详细信息
ISBN:
(纸本)160560352X
Over the past few years, the notion of stability in data clustering has received growing attention as a cluster validation criterion in a sample-based framework. However, recent work has shown that as the sample size increases, any clustering model will usually become asymptotically stable. This led to the conclusion that stability is lacking as a theoretical and practical tool. The discrepancy between this conclusion and the success of stability in practice has remained an open question, which we attempt to address. Our theoretical approach is that stability, as used by cluster validation algorithms, is similar in certain respects to measures of generalization in a model-selection framework. In such cases, the model chosen governs the convergence rate of generalization bounds. By arguing that these rates are more important than the sample size, we are led to the prediction that stability-based cluster validation algorithms should not degrade with increasing sample size, despite the asymptotic universal stability. This prediction is substantiated by a theoretical analysis as well as some empirical results. We conclude that stability remains a meaningful cluster validation criterion over finite samples.
Clustering Stability methods are a family of widely used model selection techniques applied in data clustering. Their unifying theme is that an appropriate model should result in a clustering which is robust with resp...
详细信息
Clustering Stability methods are a family of widely used model selection techniques applied in data clustering. Their unifying theme is that an appropriate model should result in a clustering which is robust with respect to various kinds of perturbations. Despite their relative success, not much is known theoretically on why or when do they work, or even what kind of assumptions they make in choosing an 'appropriate' model. Moreover, recent theoretical work has shown that they might 'break down' for large enough samples. In this paper, we focus on the behavior of clustering stability using k-means clustering. Our main technical result is an exact characterization of the distribution to which suitably scaled measures of instability converge, based on a sample drawn from any distribution in Rn satisfying mild regularity conditions. From this, we can show that clustering stability does not 'break down' even for arbitrarily large samples, in the k-means framework that we study. Moreover, it allows us to identify the factors which influence the behavior of clustering stability for any sample size. This leads to some interesting preliminary observations about what kind of assumptions are made when using these methods. While often reasonable, these assumptions might also lead to unexpected consequences.
This paper suggests a new approach to measurement of parameters in an extremely unstable chaotic system. A new notion of 'ordered space' is introduced to measure the relationship between external signal and ch...
详细信息
This paper suggests a new approach to measurement of parameters in an extremely unstable chaotic system. A new notion of 'ordered space' is introduced to measure the relationship between external signal and chaotic orbit. The new theory proposed is the foundation of chaotic information processing.
暂无评论