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 tackle the problem of subgraph isomorphism detection on large graphs, which may commonly be intractable, even with state of the art algorithms. Rather than competing with other matching algorithms, we define enhancements that can be used by (almost) any subgraph isomorphism algorithm, both current and future. These enhancements consist of a number of topological features to be added to the nodes, and a technique which we term “iterative node elimination”. The fusion of these enhancements is shown to be able to reduce subgraph isomorphism matching times by a factor of over 4,500.

/pdf/topological-features-and-iterative-node-elimination-for-4bvqe4c9nu.pdf

Topological features and iterative node elimination for speeding up subgraph isomorphism detection

Interactively Matching Hand-Drawings Using Induction

Inertial sensors, such as accelerometers and gyroscopes, are rarely used by themselves to compute velocity and position as each requires the integration of very noisy data. The variance and bias in the resulting position and velocity estimates grow unbounded in time. This paper proposes a solution to provide a de-biased and de-noised estimation of position and velocity of human actions from accelerometer measurements. The method uses a continuous wavelet transform applied to the measurements recursively to provide reliable action trajectory reconstruction. The results are presented from experiments performed with a MEMS accelerometer and gyroscope.

Action trajectory reconstruction from inertial sensor measurements

Summasy.-The underestimation of transverse extent relative to longitudinal extent, in the Poggendorff Illusion, was tested by varying oblique line orientation, interparallel line distance, and presence or absence of obliques. 20 subjects made estimates of the transverse extent on both a longitudinal and transverse extent. The results indicated that, although underestimation was found for some stimulus conditions, overestimation was found for others. It was argued that even though presence of obliques affected judgmental error the longitudinal-transverse illusion could not form a basis for the Poggendorff Illusion. The usual form of the Poggendorff figure consists of a pair of vertically oriented parallel lines which separate two collinear oblique lines. The illusion refers to the apparenc lack of collinearity between the two oblique line segments. This apparent misalignment of the oblique lines has been shown to vary with the distance between the parallels (Hotopf & Ollerearnshaw, 1972b) and the angle of the obliques to vertical (Leibowitz & Toffey, 1966). Weintraub and Krantz (1971) have proposed the following relationship between illusion extent (I), distance (D) and angle (O), I = 0.162 (D tan 8). A similar formulation derived from a Lie Algebra explanation of constancy phenomena (Hoffman, 197 1 ) has been suggested by Caeli, Finlay, and Hall (in press). The recent upsurge of interest in che Poggendorff figure (Chiang, 1968; Coren, 1969; Day, 1973;:: Restle, 1969; Walker, 1973) has thrown into question many of the explanacions for the ill~ision. For instance, the tendency to see acute angles as increased in size, as a basis for the illusion (Hering, 1861), has been shown co be inadequate (Hotopf & Ollerearnshaw, 1972a, 1972b; Weintraub & Krantz, 1971). A new explanation of the illusion has recencly been offered. In a series of experiments in which a variable longitudinal extent was matched to a transverse extent, it was shown that the oblique transverse extent, i.e., distance between the obliques, was underestimated by about 10% when the obliques formed an angle of 45'. It was claimed that this underestimation formed the basis of the illusion and was a consequence of a distortion of the space between the parallels and intersections. As further evidence of this distortion it was shown that the angle formed by the transverse extent in this space was underestimated. Day recognized that chis explanation replaced one ill~ision by anocher. "A central issue, 'N.S.W., 2308, Australia. X. H. Day. Explanation of the Poggendorff misalignment illusion. (Unpublished manuscript, Monash Univer., 1974)

The Poggendorff Illusion and estimates of transverse extent.

3D insect models are useful to overcome viewing angle variations and self-occlusions in computer-assisted insect taxonomy for electronic field guides. The acquisition of 3D information is, however, unreliable due to the flexibility and small size of the insect bodies. This paper explores how to infer 3D insect models from a single 2D insect image, which will assist both insect description and identification. The 3D structure of the insect body is modeled from two geometric primitives, generalized cylinders and deformable ellipsoids. The primitives are fitted and warped based on both edge and medial axis constraints of the 2D image. Individualized 3D models are then built to approximate the insect structure. The proposed approach results in seemingly useful 3D insect models capable of representing the major morphological characteristics for a variety of insects with different body types. This method could be a helpful assistance for computer-assisted insect taxonomy and insect identification by entomologists and the public.

/pdf/primitive-based-3d-structure-inference-from-a-single-2d-228yga1847.pdf

Terry Caelli

Papers

Topological features and iterative node elimination for speeding up subgraph isomorphism detection

Interactively Matching Hand-Drawings Using Induction

Action trajectory reconstruction from inertial sensor measurements

The Poggendorff Illusion and estimates of transverse extent.

Primitive-based 3D structure inference from a single 2D image for insect modeling: Towards an electronic field guide for insect identification