Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

I have developed "tennis elbow" from lugging this book around the past four weeks, but it is worth the pain, the effort, and the aspirin. It is also worth the (relatively speaking) bargain price. Including appendixes, this book contains 894 pages of text. The entire panorama of the neural sciences is surveyed and examined, and it is comprehensive in its scope, from genomes to social behaviors. The editors explicitly state that the book is designed as "an introductory text for students of biology, behavior, and medicine," but it is hard to imagine any audience, interested in any fragment of neuroscience at any level of sophistication, that would not enjoy this book. The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or

Principles of Neural Science

In this paper we propose a novel approach for detecting interest points invariant to scale and affine transformations. Our scale and affine invariant detectors are based on the following recent results: (1) Interest points extracted with the Harris detector can be adapted to affine transformations and give repeatable results (geometrically stable). (2) The characteristic scale of a local structure is indicated by a local extremum over scale of normalized derivatives (the Laplacian). (3) The affine shape of a point neighborhood is estimated based on the second moment matrix.

Our scale invariant detector computes a multi-scale representation for the Harris interest point detector and then selects points at which a local measure (the Laplacian) is maximal over scales. This provides a set of distinctive points which are invariant to scale, rotation and translation as well as robust to illumination changes and limited changes of viewpoint. The characteristic scale determines a scale invariant region for each point. We extend the scale invariant detector to affine invariance by estimating the affine shape of a point neighborhood. An iterative algorithm modifies location, scale and neighborhood of each point and converges to affine invariant points. This method can deal with significant affine transformations including large scale changes. The characteristic scale and the affine shape of neighborhood determine an affine invariant region for each point.

We present a comparative evaluation of different detectors and show that our approach provides better results than existing methods. The performance of our detector is also confirmed by excellent matching resultss the image is described by a set of scale/affine invariant descriptors computed on the regions associated with our points.

/pdf/scale-affine-invariant-interest-point-detectors-189ragelfl.pdf

Scale & Affine Invariant Interest Point Detectors

A method for rapid visual recognition of personal identity is described, based on the failure of a statistical test of independence. The most unique phenotypic feature visible in a person's face is the detailed texture of each eye's iris. The visible texture of a person's iris in a real-time video image is encoded into a compact sequence of multi-scale quadrature 2-D Gabor wavelet coefficients, whose most-significant bits comprise a 256-byte "iris code". Statistical decision theory generates identification decisions from Exclusive-OR comparisons of complete iris codes at the rate of 4000 per second, including calculation of decision confidence levels. The distributions observed empirically in such comparisons imply a theoretical "cross-over" error rate of one in 131000 when a decision criterion is adopted that would equalize the false accept and false reject error rates. In the typical recognition case, given the mean observed degree of iris code agreement, the decision confidence levels correspond formally to a conditional false accept probability of one in about 10/sup 31/. >

/pdf/high-confidence-visual-recognition-of-persons-by-a-test-of-k27n96b3kx.pdf

High confidence visual recognition of persons by a test of statistical independence

The emerging viewpoint of embodied cognition holds that cognitive processes are deeply rooted in the body’s interactions with the world. This position actually houses a number of distinct claims, some of which are more controversial than others. This paper distinguishes and evaluates the following six claims: (1) cognition is situated; (2) cognition is time-pressured; (3) we off-load cognitive work onto the environment; (4) the environment is part of the cognitive system; (5) cognition is for action; (6) offline cognition is body based. Of these, the first three and the fifth appear to be at least partially true, and their usefulness is best evaluated in terms of the range of their applicability. The fourth claim, I argue, is deeply problematic. The sixth claim has received the least attention in the literature on embodied cognition, but it may in fact be the best documented and most powerful of the six claims.

/pdf/six-views-of-embodied-cognition-2l6klwi201.pdf

Six views of embodied cognition.

In this paper, we show how inexact graph matching (that is, the correspondence between sets of vertices of pairs of graphs) can be solved using the renormalization of projections of the vertices (as defined in this case by their connectivities) into the joint eigenspace of a pair of graphs and a form of relational clustering. An important feature of this eigenspace renormalization projection clustering (EPC) method is its ability to match graphs with different number of vertices. Shock graph-based shape matching is used to illustrate the model and a more objective method for evaluating the approach using random graphs is explored with encouraging results.

An eigenspace projection clustering method for inexact graph matching

In Part I Caelli and Julesz generated texture pairs of 4-disk micropatterns with identical dipole statistics. They found that this iso-dipole constraint could not prevent the quasi-collinearity of certain disk elements which, in turn, yielded effortless discrimination. They proposed two classes of perceptual analyzers to explain discrimination with these micropatern textures: Class A, corresponding to those which detect dipole differences; while Class B detectors, such as the quasi-collinear detector (QCD), acted when isodipole textures were presented. In this paper we show several new methods for generating iso-dipole textures with micropatterns consisting of 5 or more disks or non-disk shaped elements, and we report the discovery of two other Class B detectors, a corner detector (using a 6-disk method), and a closure detector (with 8---11 disk micropatterns). These QCD, corner, and closure detectors were verified by examining several hundred iso-dipole texture pairs. It appears that iso-dipole constraints make ineffective all other feature analyzers involved in effortless texture discrimination than the Class B types. These figural properties of collinearity, corners, and closure can be perceived without scrutiny and are precursors of form perception.

On perceptual analyzers underlying visual texture discrimination: Part II

On the classification of image regions by colour, texture and shape

This paper describes a novel solution to the rigid point pattern matching problem in Euclidean spaces of any dimension. Although we assume rigid motion, jitter is allowed. We present a noniterative, polynomial time algorithm that is guaranteed to find an optimal solution for the noiseless case. First, we model point pattern matching as a weighted graph matching problem, where weights correspond to Euclidean distances between nodes. We then formulate graph matching as a problem of finding a maximum probability configuration in a graphical model. By using graph rigidity arguments, we prove that a sparse graphical model yields equivalent results to the fully connected model in the noiseless case. This allows us to obtain an algorithm that runs in polynomial time and is provably optimal for exact matching between noiseless point sets. For inexact matching, we can still apply the same algorithm to find approximately optimal solutions. Experimental results obtained by our approach show improvements in accuracy over current methods, particularly when matching patterns of different sizes

http://users.cecs.anu.edu.au/~caetano/PAMI05.pdf

Graphical Models and Point Pattern Matching

In this correspondence, the application of covariance techniques to surface representation of 3-D objects is discussed and such ways of computing surface geometry are compared with traditional methods using differential geometry. It is shown how the covariance method provides surface descriptors that are invariant to rigid motions without explicitly using surface parameterizations or derivatives. Analogous covariance operators for both the Gauss and Weingarten maps are defined and a range image segmentation technique is presented that labels pixels as jump or crease discontinuities or planar, parabolic or curved region types. >

Terry Caelli

Papers

An eigenspace projection clustering method for inexact graph matching

On perceptual analyzers underlying visual texture discrimination: Part II

On the classification of image regions by colour, texture and shape

Graphical Models and Point Pattern Matching

Computation of surface geometry and segmentation using covariance techniques