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

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

How to Do Things With Words

Recent studies of eye movements in reading and other information processing tasks, such as music reading, typing, visual search, and scene perception, are reviewed. The major emphasis of the review is on reading as a specific example of cognitive processing. Basic topics discussed with respect to reading are (a) the characteristics of eye movements, (b) the perceptual span, (c) integration of information across saccades, (d) eye movement control, and (e) individual differences (including dyslexia). Similar topics are discussed with respect to the other tasks examined. The basic theme of the review is that eye movement data reflect moment-to-moment cognitive processes in the various tasks examined. Theoretical and practical considerations concerning the use of eye movement data are also discussed.

/pdf/eye-movements-in-reading-and-information-processing-20-years-3z5ay8hdwc.pdf

Eye movements in reading and information processing: 20 years of research.

This article is a review of the literature on classroom formative assessment. Several studies show firm evidence that innovations designed to strengthen the frequent feedback that students receive about their learning yield substantial learning gains. The perceptions of students and their role in self‐assessment are considered alongside analysis of the strategies used by teachers and the formative strategies incorporated in such systemic approaches as mastery learning. There follows a more detailed and theoretical analysis of the nature of feedback, which provides a basis for a discussion of the development of theoretical models for formative assessment and of the prospects for the improvement of practice.

Assessment and Classroom Learning

The goal of this chapter is to provide the foundation toward developing a more comprehensive model of reading comprehension. To this end, seven prominent comprehension models (Construction–Integration, Structure-Building, Resonance, Event-Indexing, Causal Network, Constructionist, and Landscape) are described, evaluated, and compared. We describe what comprehension models have offered thus far, differences and similarities between them, and what comprehension processes are not included within any of the models, and thus, what should be included in a comprehensive model. Our primary conclusion from the review of this literature is that current models of comprehension are not necessarily contradictory, but rather cover different spectrums of comprehension processes. Further, no one model adequately accounts for a wide variety of reading situations that have been observed and the range of comprehension considered thus far in comprehension models is too limited.

Chapter 9 Toward a Comprehensive Model of Comprehension

Dimensions of situation model construction in narrative comprehension.

Naturalistic one-to-one tutoring is more effective than traditional classroom teaching methods, but there have been few attempts to examine the features of normal tutoring that might explain its advantage. This project explored dialogue patterns in two samples of naturalistic tutoring with normal unskilled tutors (as opposed to expert tutors): graduate students tutoring undergraduates in research methods and high school students tutoring 7th graders in algebra. We analysed the extent to which those tutoring protocols manifested components that have been emphasized in contemporary pedagogical theories and intelligent tutoring systems: active student learning, sophisticated pedagogical strategies, specific examples and cases, collaborative problem solving and question answering, deep explanatory reasoning, convergance toward shared meanings, feedback, error diagnosis and remediation, and affect. The most prominent components consisted of collaborative problem solving, question answering, and explanation in the context of specific examples. We identify frequent dialogue patterns that characterize these collaborative processes.

Collaborative dialogue patterns in naturalistic one-to-one tutoring

This study investigated conscious understanding during narrative comprehension as revealed through the use of think‐aloud methodology. An analytical model of conscious understanding is presented, which assumes that inference and memory processes function together in order to construct a coherent, mental representation of a text. Three working memory operations were operationally identified in the think‐aloud protocols: (1) activation of relevant world knowledge in working memory, (2) maintenance of information in working memory, and (3) retrieval of text and prior thoughts from a long‐term memory store. These memory operations are functionally necessary to three kinds of inferences that also occurred in the protocols: (1) explanation, (2) association, and (3) prediction. The data revealed that understanding is, for the most part, explanation based. Memory processes serve to provide the information that readers use to explain sentences or thoughts that occur while they try to understand the text. Coherent ...

Conscious understanding during comprehension

This study addresses 3 questions: How flexible are readers when reading strategically? How is strategic processing affected by properties of the text? and Do some strategies lead to better text retention than others? Participants read short narratives and thought aloud with an instruction to either explain, predict, associate, or understand. The think-aloud protocols were used to predict sentence reading times for other participants who read silently with the same strategies. The results indicated that readers are capable of strategically controlling the inferences that they generate. However, strategic control comes at some cost in that it limits the resources devoted to other inferences. Furthermore, strategic processing is heavily constrained by a text. Text-based explanations occurred when there was an identifiable causal antecedent in the prior text. Knowledge-based inferences occurred when there were no antecedents and when new characters and objects were introduced. These effects occurred across reading strategies. Reading to explain led to better memory, but only when reading silently.

Joseph P. Magliano

Papers

Chapter 9 Toward a Comprehensive Model of Comprehension

Dimensions of situation model construction in narrative comprehension.

Collaborative dialogue patterns in naturalistic one-to-one tutoring

Conscious understanding during comprehension

Strategic processing during comprehension.