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

Brains, it has recently been argued, are essentially prediction machines. They are bundles of cells that support perception and action by constantly attempting to match incoming sensory inputs with top-down expectations or predictions. This is achieved using a hierarchical generative model that aims to minimize prediction error within a bidirectional cascade of cortical processing. Such accounts offer a unifying model of perception and action, illuminate the functional role of attention, and may neatly capture the special contribution of cortical processing to adaptive success. This target article critically examines this "hierarchical prediction machine" approach, concluding that it offers the best clue yet to the shape of a unified science of mind and action. Sections 1 and 2 lay out the key elements and implications of the approach. Section 3 explores a variety of pitfalls and challenges, spanning the evidential, the methodological, and the more properly conceptual. The paper ends (sections 4 and 5) by asking how such approaches might impact our more general vision of mind, experience, and agency.

/pdf/whatever-next-predictive-brains-situated-agents-and-the-epj56cs868.pdf

Whatever next? Predictive brains, situated agents, and the future of cognitive science

The theory of affordances

Many current neurophysiological, psychophysical, and psychological approaches to vision rest on the idea that when we see, the brain produces an internal representation of the world. The activation of this internal representation is assumed to give rise to the experience of seeing. The problem with this kind of approach is that it leaves unexplained how the existence of such a detailed internal representation might produce visual consciousness. An alternative proposal is made here. We propose that seeing is a way of acting. It is a particular way of exploring the environment. Activity in internal representations does not generate the experience of seeing. The outside world serves as its own, external, representation. The experience of seeing occurs when the organism masters what we call the governing laws of sensorimotor contingency. The advantage of this approach is that it provides a natural and principled way of accounting for visual consciousness, and for the differences in the perceived quality of sensory experience in the different sensory modalities. Several lines of empirical evidence are brought forward in support of the theory, in particular: evidence from experiments in sensorimotor adaptation, visual \"filling in,\" visual stability despite eye movements, change blindness, sensory substitution, and color perception.

A sensorimotor account of vision and visual consciousness-Authors' Response-Acting out our sensory experience

Many current neurophysiological, psychophysical, and psychological approaches to vision rest on the idea that when we see, the brain produces an internal representation of the world. The activation of this internal representation is assumed to give rise to the experience of seeing. The problem with this kind of approach is that it leaves unexplained how the existence of such a detailed internal representation might produce visual consciousness. An alternative proposal is made here. We propose that seeing is a way of acting. It is a particular way of exploring the environment. Activity in internal representations does not generate the experience of seeing. The outside world serves as its own, external, representation. The experience of seeing occurs when the organism masters what we call the governing laws of sensorimotor contingency. The advantage of this approach is that it provides a natural and principled way of accounting for visual consciousness, and for the differences in the perceived quality of sensory experience in the different sensory modalities. Several lines of empirical evidence are brought forward in support of the theory, in particular: evidence from experiments in sensorimotor adaptation, visual “filling in,” visual stability despite eye movements, change blindness, sensory substitution, and color perception.

/pdf/a-sensorimotor-account-of-vision-and-visual-consciousness-1o8kf5szfs.pdf

A sensorimotor account of vision and visual consciousness

Book synopsis: What are the processes, from conception to adulthood, that enable a single cell to grow into a sentient adult? The processes that occur along the way are so complex that any attempt to understand development necessitates a multi-disciplinary approach, integrating data from cognitive studies, computational work, and neuroimaging - an approach till now seldom taken in the study of child development.

Neuroconstructivism is a major new 2 volume publication that seeks to redress this balance, presenting an integrative new framework for considering development. In the first volume, the authors review up-to-to date findings from neurobiology, brain imaging, child development, computer and robotic modelling to consider why children's thinking develops the way it does. They propose a new synthesis of development that is based on 5 key principles found to operate at many levels of descriptions. They use these principles to explain what causes a number of key developmental phenomena, including infants' interacting with objects, early social cognitive interactions, and the causes of dyslexia. The "neuroconstructivist" framework also shows how developmental disorders do not arise from selective damage to the normal cognitive system, but instead arise from atypical constraints. How these principles work is illustrated in several case studies ranging from perceptual to social and reading development. Finally, the authors use neuroimaging, behavioural analyses, computational simulations and robotic models to provide a way of understanding the mechanisms and processes that cause development to occur.

Neuroconstructivism - I: How the Brain Constructs Cognition

http://grammar.ucsd.edu/courses/hdp1/Readings/Mareschal_infant_categor.pdf

Categorization in infancy

We used cascade-correlation to model human cognitive development on a well studied psychological task, the balance scale. In balance scale experiments, the child is asked to predict the outcome of placing certain numbers of equal weights at various distances to the left or right of a fulcrum. Both stage progressions and information salience effects have been found with children on this task. Cascade-correlation is a generative connectionist algorithm that constructs its own network topology as it learns. Cascade-correlation networks provided better fits to these human data than did previous models, whether rule-based or connectionist. The network model was used to generate a variety of novel predictions for psychological research.

/pdf/modeling-cognitive-development-on-balance-scale-phenomena-1id1m4rtig.pdf

Modeling Cognitive Development on Balance Scale Phenomena

Human adults can go beyond the limits of individual sensory systems’ resolutions by integrating multiple estimates (e.g., vision and touch) to reduce uncertainty. Little is known about how this ability develops. Although some multisensory abilities are present from early infancy, it is not until age ≥8 y that children use multiple modalities to reduce sensory uncertainty. Here we show that uncertainty reduction by sensory integration does not emerge until 12 y even within the single modality of vision, in judgments of surface slant based on stereoscopic and texture information. However, adults’ integration of sensory information comes at a cost of losing access to the individual estimates that feed into the integrated percept (“sensory fusion”). By contrast, 6-y-olds do not experience fusion, but are able to keep stereo and texture information separate. This ability enables them to outperform adults when discriminating stimuli in which these information sources conflict. Further, unlike adults, 6-y-olds show speed gains consistent with following the fastest-available single cue. Therefore, whereas the mature visual system is optimized for reducing sensory uncertainty, the developing visual system may be optimized for speed and for detecting sensory conflicts. Such conflicts could provide the error signals needed to learn the relationships between sensory information sources and to recalibrate them while the body is growing.

https://www.pnas.org/content/pnas/early/2010/09/03/1001699107.full.pdf

Fusion of visual cues is not mandatory in children

Young infants show unexplained asymmetries in the exclusivity of categories formed on the basis of visually presented stimuli A connectionist model is described that shows similar exclusivity asymmetries when categorizing the same stimuli presented to infants The asymmetries can be explained in terms of an associative learning mechanism, distributed internal representations, and the statistics of the feature distributions in the stimuli The model was used to explore the robustness of this asymmetry The model predicts that the asymmetry will persist when a category is acquired in the presence of mixed category exemplars An experiment with 3-4-month-olds showed that asymmetric exclusivity persisted in the presence of mixed-exemplar familiarization, thereby confirming the model's prediction

/pdf/a-connectionist-account-of-asymmetric-category-learning-in-4bbal6c5d9.pdf

Denis Mareschal

Papers

Neuroconstructivism - I: How the Brain Constructs Cognition

Categorization in infancy

Modeling Cognitive Development on Balance Scale Phenomena

Fusion of visual cues is not mandatory in children

A connectionist account of asymmetric category learning in early infancy.