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

Modeling visual attention-particularly stimulus-driven, saliency-based attention-has been a very active research area over the past 25 years. Many different models of attention are now available which, aside from lending theoretical contributions to other fields, have demonstrated successful applications in computer vision, mobile robotics, and cognitive systems. Here we review, from a computational perspective, the basic concepts of attention implemented in these models. We present a taxonomy of nearly 65 models, which provides a critical comparison of approaches, their capabilities, and shortcomings. In particular, 13 criteria derived from behavioral and computational studies are formulated for qualitative comparison of attention models. Furthermore, we address several challenging issues with models, including biological plausibility of the computations, correlation with eye movement datasets, bottom-up and top-down dissociation, and constructing meaningful performance measures. Finally, we highlight current research trends in attention modeling and provide insights for future.

State-of-the-Art in Visual Attention Modeling

Based on concepts of the human visual system, computational visual attention systems aim to detect regions of interest in images. Psychologists, neurobiologists, and computer scientists have investigated visual attention thoroughly during the last decades and profited considerably from each other. However, the interdisciplinarity of the topic holds not only benefits but also difficulties: Concepts of other fields are usually hard to access due to differences in vocabulary and lack of knowledge of the relevant literature. This article aims to bridge this gap and bring together concepts and ideas from the different research areas. It provides an extensive survey of the grounding psychological and biological research on visual attention as well as the current state of the art of computational systems. Furthermore, it presents a broad range of applications of computational attention systems in fields like computer vision, cognitive systems, and mobile robotics. We conclude with a discussion on the limitations and open questions in the field.

/pdf/computational-visual-attention-systems-and-their-cognitive-3c1msw6bdy.pdf

Computational visual attention systems and their cognitive foundations: A survey

A system and method of detecting an aberrant message is provided. An ordered set of words within the message is detected. The set of words found within the message is linked to a corresponding set of expected words, the set of expected words having semantic attributes. A set of grammatical structures represented in the message is detected, based on the ordered set of words and the semantic attributes of the corresponding set of expected words. A cognitive noise vector comprising a quantitative measure of a deviation between grammatical structures represented in the message and an expected measure of grammatical structures for a message of the type is then determined. The cognitive noise vector may be processed by higher levels of the neural network and/or an external processor.

Intelligent control with hierarchical stacked neural networks

We develop an architecture for reactive visual analysis of dynamic scenes. We specify a minimal set of system features based upon biological observations. We implement feature on a processing network based around an active stereo vision mechanism. Active rectification and mosaicing allows static stereo algorithms to operate on the active platform. Foveal zero disparity operations permit attended object extraction and ensures coordinated stereo fixation upon visual surfaces. Activedynamic inhibition of return, and task dependent biasing result in a flexible, preemptive and retrospective system that responds to unique visual stimuli and is capable of top-down modulation of attention towards regions and cues relevant to tasks.

/pdf/a-reactive-vision-system-active-dynamic-saliency-4sq66o4uky.pdf

A Reactive Vision System: Active-Dynamic Saliency

We report on the development of a multi-purpose active visual sensor system for real-world application. The C abl e - D rive A ctive-Vision R obot, CeDAR, has been designed for use on a diverse range of platforms to perform a diverse range of tasks. The novel, biologically inspired design has evolved from a systems-based approach. The mechanism is compact and lightweight and is capable of motions that exceed human visual performance and earlier mechanical designs. The control system complements the mechanical design to implement the basic visual behaviours of fixation, smooth pursuit and saccade, with stability during high-speed motions, high precision and repeatability. Real-time algorithms have been developed that process stereo colour images, resulting in a suite of basic visual competencies. We have developed a scheme to fuse the results of the visual algorithms into robust task-oriented behaviours by adopting a statistical framework. CeDAR has been successfully used for experiments in autonomous vehicle guidance, object tracking and visual sensing for mobile robot experiments.

CeDAR: A real-world vision system: Mechanism, control and visual processing

The invention proposes a system that uses a novel method to analyze the surface being about to be traversed by a vehicle. The system can be used to enhance vehicle safety and control. The system makes use of AER cameras such as the Silicon Retina. The Silicon Retina is used monitor the surface to be traversed, and a processing unit analyzes the surface based on the signal provided by the Silicon Retina. The proposed surface analysis method carried out by the system surpasses state-of-art analysis methods.

Analyzing road surfaces

http://users.rsise.anu.edu.au/~nmb/papers/Dankers_CVIU05.pdf

MAP ZDF segmentation and tracking using active stereo vision: Hand tracking case study

We present a mapping approach to scene understanding based on active stereo vision. We generalise traditional static multi-camera rectification techniques to enable active epipolar rectification and intuitive representation of the results. The approach is shown to enable the use of any static stereo algorithms with active multi-camera systems. In particular, we show the use of the framework to apply static depthmapping techniques to the active case. Further, we outline the benefits of using an occupancy grid framework for the fusion and representation of range data, and find that it is especially suited for active vision. Finally, we provide a preview of our approach to dynamic occupancy grids for scene understanding.

/pdf/active-vision-rectification-and-depth-mapping-13683hghtt.pdf

Andrew Dankers

Papers

A Reactive Vision System: Active-Dynamic Saliency

CeDAR: A real-world vision system: Mechanism, control and visual processing

Analyzing road surfaces

MAP ZDF segmentation and tracking using active stereo vision: Hand tracking case study

Active Vision - Rectification and Depth Mapping