Verbal reasoning

About: Verbal reasoning is a research topic. Over the lifetime, 2604 publications have been published within this topic receiving 97085 citations. The topic is also known as: verbal logic.

Case-based reasoning

Abstract: Case-based reasoning is one of the fastest growing areas in the field of knowledge-based systems and this book, authored by a leader in the field, is the first comprehensive text on the subject. Case-based reasoning systems are systems that store information about situations in their memory. As new problems arise, similar situations are searched out to help solve these problems. Problems are understood and inferences are made by finding the closest cases in memory, comparing and contrasting the problem with those cases, making inferences based on those comparisons, and asking questions when inferences can't be made. This book presents the state of the art in case-based reasoning. The author synthesizes and analyzes a broad range of approaches, with special emphasis on applying case-based reasoning to complex real-world problem-solving tasks such as medical diagnosis, design, conflict resolution, and planning. The author's approach combines cognitive science and engineering, and is based on analysis of both expert and common-sense tasks. Guidelines for building case-based expert systems are provided, such as how to represent knowledge in cases, how to index cases for accessibility, how to implement retrieval processes for efficiency, and how to adapt old solutions to fit new situations. This book is an excellent text for courses and tutorials on case-based reasoning. It is also a useful resource for computer professionals and cognitive scientists interested in learning more about this fast-growing field.

Toward memory-based reasoning

Abstract: The intensive use of memory to recall specific episodes from the past—rather than rules—should be the foundation of machine reasoning.

Early Intervention and Language Development in Children Who Are Deaf and Hard of Hearing

Abstract: Objective. The primary purpose of this study was to examine the relationship between age of enrollment in intervention and language outcomes at 5 years of age in a group of deaf and hard-of-hearing children. Method. Vocabulary skills at 5 years of age were examined in a group of 112 children with hearing loss who were enrolled at various ages in a comprehensive intervention program. Verbal reasoning skills were explored in a subgroup of 80 of these children. Participants were evaluated using the Peabody Picture Vocabulary Test and a criterion-referenced measure, the Preschool Language Assessment Instrument, administered individually by professionals skilled in assessing children with hearing loss. A rating scale was developed to characterize the level of family involvement in the intervention program for children in the study. Results. A statistically significant negative correlation was found between age of enrollment and language outcomes at 5 years of age. Children who were enrolled earliest (eg, by 11 months of age) demonstrated significantly better vocabulary and verbal reasoning skills at 5 years of age than did later-enrolled children. Regardless of degree of hearing loss, early-enrolled children achieved scores on these measures that approximated those of their hearing peers. In an attempt to understand the relationships among performance and factors, such as age of enrollment, family involvement, degree of hearing loss, and nonverbal intelligence, multiple regression models were applied to the data. The analyses revealed that only 2 of these factors explained a significant amount of the variance in language scores obtained at 5 years of age: family involvement and age of enrollment. Surprisingly, family involvement explained the most variance after controlling for the influence of the other factors ( r = .615; F change = 58.70), underscoring the importance of this variable. Age of enrollment also contributed significantly to explained variance after accounting for the other variables in the regression ( r = −.452; F change = 19.24). Importantly, there were interactions between the factors of family involvement and age of enrollment that influenced outcomes. Early enrollment was of benefit to children across all levels of family involvement. However, the most successful children in this study were those with high levels of family involvement who were enrolled early in intervention services. Late-identified children whose families were described as limited or average in involvement scored >2 standard deviations below their hearing peers at 5 years of age. Even in the best of circumstances (eg, early enrollment paired with high levels of family involvement), the children in this study scored within the low average range in abstract verbal reasoning compared with hearing peers, reflecting qualitative language differences in these groups of children. Conclusions. Consistent with the findings of Yoshinaga-Itano et al, 1 significantly better language scores were associated with early enrollment in intervention. High levels of family involvement correlated with positive language outcomes, and, conversely, limited family involvement was associated with significant child language delays at 5 years of age, especially when enrollment in intervention was late. The results suggest that success is achieved when early identification is paired with early interventions that actively involve families.

CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

Abstract: When building artificial intelligence systems that can reason and answer questions about visual data, we need diagnostic tests to analyze our progress and discover short-comings. Existing benchmarks for visual question answering can help, but have strong biases that models can exploit to correctly answer questions without reasoning. They also conflate multiple sources of error, making it hard to pinpoint model weaknesses. We present a diagnostic dataset that tests a range of visual reasoning abilities. It contains minimal biases and has detailed annotations describing the kind of reasoning each question requires. We use this dataset to analyze a variety of modern visual reasoning systems, providing novel insights into their abilities and limitations.