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

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Co-Planar Stereotaxic Atlas of the Human Brain—3-Dimensional Proportional System: An Approach to Cerebral Imaging, J. Talairach, P. Tournoux. Georg Thieme Verlag, New York (1988), 122 pp., 130 figs. DM 268

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

How to Do Things With Words

We present AKIRA, an agent-based hybrid architecture designed for cognitive modeling. We describe some of the underlying ideas motivating its development, such as the possibility of exploiting distributed representations and performing parallel, dynamic and context aware computation. We illustrate its main components and capabilities and compare it with some related cognitive architectures, such as DUAL and Copycat. We present also a sample simulation in the visual search domain, exploiting AKIRA's peculiarities for cognitive modeling.

Dynamic computation and context effects in the hybrid architecture AKIRA

In this study, we asked whether the event-related potentials associated to cue and target stimuli of a Central Cue Posner Paradigm (CCPP) may encode key parameters of Bayesian inference - prior expectation and surprise - on a trial-by-trial basis. Thirty-two EEG channel were recorded in a sample of 19 young adult subjects while performing a CCPP, in which a cue indicated (validly or invalidly) the position of an incoming auditory target. Three different types of blocks with validities of 50%, 64%, and 88%, respectively, were presented. Estimates of prior expectation and surprise were obtained on a trial-by-trial basis from participants' responses, using a computational model implementing Bayesian learning. These two values were correlated on a trial-by-trial basis with the EEG values in all the electrodes and time bins. Therefore, a Spearman correlation metrics of the relationship between Bayesian parameters and the EEG was obtained. We report that the surprise parameter was able to classify the different validity blocks. Furthermore, the prior expectation parameter showed a significant correlation with the EEG in the cue-target period, in which the Contingent Negative Variation develops. Finally, in the post-target period the surprise parameter showed a significant correlation in the latencies and electrodes in which different event-related potentials are induced. Our results suggest that Bayesian parameters are coded in the EEG signals; and namely, the CNV would be related to prior expectation, while the post-target components P2a, P2, P3a, P3b, and SW would be related to surprise. This study thus provides novel support to the idea that human electrophysiological neural activity may implement a (Bayesian) predictive processing scheme.

/pdf/tracking-the-time-course-of-bayesian-inference-with-event-5fwgfwz781.pdf

Tracking the Time Course of Bayesian Inference With Event-Related Potentials:A Study Using the Central Cue Posner Paradigm.

In this study we describe visuospatial working memory and visual mental imagery of a child with Cerebral Palsy. Beyond a moderate impairment of visuomotor integration skills, cognitive level and memory span, poor performance emerged in figures reconstruction, in memorizing matrix patterns and movements along a path. No such deficits were observed in recalling figures and their positions on a grid and learning groups of words using a visual imagery strategy. This case highlights that impaired action execution impairs performance in imagery tasks as well, but not when alternative strategies (e.g., verbal encoding) can be adopted. Results are discussed considering recent evidence on working memory and visual imagery links, and their role in motor rehabilitation training.

Working memory and mental imagery in Cerebral Palsy: A single case investigation

Behavioural and neuroimaging studies provide evidence of automatic activation of phonology (e.g., covert speech) during the recognition of lexical stimuli. Implicit processing of phonological information was investigated in a kinematic study of semantic categorisation of pictures (session A) or words (session B). Participants clicked one of two items (target and distractor) based on their semantic congruency (artefact or natural) with a cued-word. Phonological similarity between cued-word and distractor was varied. The presence of the phonological distractor produced trajectories with greater curvature towards the competing semantic category than did the presence of a distractor not phonologically related. This suggests that the semantic categorisation of pictorial and lexical stimuli is influenced by the automatic activation of phonological information. Trajectories’ curvature reveals competition between partially activated phonological and semantic representations suggesting that phonological co...

Giovanni Pezzulo

Papers

Dynamic computation and context effects in the hybrid architecture AKIRA

Tracking the Time Course of Bayesian Inference With Event-Related Potentials:A Study Using the Central Cue Posner Paradigm.

Working memory and mental imagery in Cerebral Palsy: A single case investigation

The effects of phonological similarity on the semantic categorisation of pictorial and lexical stimuli: evidence from continuous behavioural measures

Embodying Markov blankets. Comment on "Answering Schrödinger's question: A free-energy formulation" by Maxwell James Désormeau Ramstead et al.