Learning and development in neural networks--the importance of prior experience

Infants can discriminate between familiar and unfamiliar grammatical patterns expressed in a vocabulary that is distinct from that used earlier during familiarization (Cognition 70(2) (1999) 109; Science 283 (1999) 77). Various models have captured the data, although each required that discrimination be distinct, in terms of the computational process, from familiarization. This article describes a simple recurrent network (SRN), equipped only with the assumption that it should predict what comes next, which models the data without distinguishing between familiarization and discrimination. To accomplish this, the SRN requires pre-training on a range of sequences instantiating different structures and different vocabulary items to those used subsequently during familiarization and test. Pre-training enables the network to avoid replacing structure acquired during familiarization with structure experienced at test. An equivalent enabling condition may underpin infants' resistance to catastrophic interference between the different structures and vocabulary items to which they are exposed.     

Do Positive Self-Perceptions Have a “Dark Side”? Examination of the Link between Perceptual Bias and Aggression

The hypothesis that positive self-perceptions may have a dark side was investigated in the present study by examining the relationship between positively biased self-perceptions and aggression. Ratings of actual and perceived social acceptance of third-grade (n = 278), fourth-grade (n = 260), and fifth-grade (n = 321) students were compared to form a measure of perceptual bias. Peers provided nominations for overt and relational aggression. Gender differences were found for aggression (males were more overtly and relationally aggressive than females) but not perceptual bias. African-American children held more positive perceptions of their social acceptance and were perceived by peers as more aggressive than Caucasian children. Even after controlling for the effects of gender and ethnicity, more positively biased perceptions were associated with more peer nominations for overt and relational aggression. Contrary to an optimal range of bias hypothesis, even moderately positive self-perceptions were associated with elevated levels of aggression.     

Making a Difference: The Social Ecology of Social Transformation

A multidisciplinary and multilevel framework for social transformation is proposed, encompassing four foundational goals: capacity-building, group empowerment, relational community-building, and culture-challenge. Intervention approaches related to each goal are presented at the setting, geographic community, and societal levels. Four exemplars of social transformation work are then discussed: the Accelerated Schools Project, Meyerhoff Program, ManKind Project, and women's movement. These examples illustrate the synergistic relationship among the four transformational goals, within and across levels of analysis, which is at the heart of the social transformation process. The paper concludes with three challenges to guide our efforts as we enter the new century: (1) to move social transformation to the center of our consciousness as a field; (2) to articulate jointly with allied disciplines, organizations, and citizen groups an encompassing, multidisciplinary, and multilevel framework for social transformation; and (3) to do the above with heart, soul, and humility.     

Toward a Comprehensive Strategy for Effective Practitioner–Scientist Partnerships and Larger-Scale Community Health and Well-Being

This article articulates joint priorities for the fields of prevention science and community psychology. These priorities are intended to address issues raised by the frequent observation of natural tensions between community practitioners and scientists. The first priority is to expand the knowledge base on practitioner–scientist partnerships, particularly on factors associated with positive outcomes within communities. To further articulate this priority, the paper first discusses the rapid growth in community-based partnerships and the emergent research on them. Next described is an illustrative research project on a partnership model that links state university extension and public school delivery systems. The article then turns to the second, related priority of future capacity-building for diffusion of effective partnership-based interventions to achieve larger-scale health and well-being across communities. It outlines two salient tasks: clarification of a conceptual framework and the formulation of a comprehensive capacity-building strategy for diffusion. The comprehensive strategy would require careful attention to the expansion of networks of effective partnerships, partnership-based research agendas, and requisite policy-making.     

A formal model for structuring local perceptions of environmental space

The problem of constructing computational models of space that mimic those found in human spatial reasoning is addressed. This paper extends a formal model that addressed point objects in a 2D world to include the presence of line objects and barriers. The problem consists of determining an appropriate global model for the spatial configuration given a sequence of local views or observations. A formal model is proposed based on constraint network theory. The model leads to the identification of stable regions within which perceptual information about the environment changes slowly, and zones of transition within which the perceptual information changes more quickly. A special case of transition zones is a gateway, which may be viewed as a kind of discontinuity or singularity in the model. It is expected that the model obtained will be used to mimic human mental representations of navigable outdoor environments.     

Psychoanalysis and empirical research

At the beginning of the nineteenth century, the idea of reason began to lose its universal and absolute value, undermining the view of science as a form of objective knowledge that reveals a fundamental reality. These changes have also had an impact on psychoanalysis, leading to a proliferation of theories and the end of a positivistic approach, epitomized by a 'neutral' analyst who knows the contents of the patient's mind. Hermeneutic philosophy provides a tool with which to explore both theoretical multiplicity and the contribution of the analyst's subjectivity to the analytic process. Furthermore, a hermeneutic approach does not have to be hostile to empirical science, but can be integrated with it in a 'scientific-hermeneutic model' in which historical and biological principles are given equal value.     

Equivalence relations in individuals with language limitations and mental retardation

The study of equivalence relations exhibited by individuals with mental retardation and language limitations holds the promise of providing information of both theoretical and practical significance. We reviewed the equivalence literature with this population, defined in terms of subjects having moderate, severe, or profound mental retardation. The literature includes 55 such individuals, most of whom showed positive outcomes on equivalence tests. The results to date suggest that naming skills are not necessary for positive equivalence test outcomes. Thus far, however, relatively few subjects with minimal language have been studied. Moreover, we suggest that the scientific contributions of studies in this area would be enhanced with better documentation of language skills and other subject characteristics. With recent advances in laboratory procedures for establishing the baseline performances necessary for equivalence tests, this research area is poised for rapid growth.     

Transitive choices by a simple, fully connected, backpropagation neural network: implications for the comparative study of transitive inference.

In search of the minimal requirements for transitive reasoning, a simple neural network was trained and tested on the non-verbal version of the conventional "five-term-series task" – a paradigm used with human adults, children and a variety of non-human species. The transitive performance of the network was analogous in several aspects to that reported for children and animals. The three effects usually associated with transitive choices i.e. "symbolic distance", "lexical marking" and "end-anchor", were also clearly shown by the neural network. In a second experiment, where the training conditions were manipulated, the network failed to match the behavioural pattern reported for human adults in the test following an ordered presentation of the premises. However, it mimicked young children's performance when tested with a novel comparison term. Although we do not intend to suggest a new model of transitive inference, we conclude, in line with other authors, that a simple error-correcting rule can generate transitive behaviour similar to the choice pattern of children and animals in the binary form of the five-term-series task without requiring high-order logical or paralogical abilities. The analysis of the training history and of the final internal structure of the network reveals the associative strategy employed. However, our results indicate that the scope of the associative strategy used by the network might be limited. The extent to which the conventional five-term-series task, in absence of appropriate manipulations of training and testing conditions, is suitable to detect cognitive differences across species is also discussed on the basis of our results. Accepted after revision: 29 May 2001 Electronic Publication     

Minority representation,tokenism, and well-being in army units

Racial and ethnic diversity is increasing in the US Army and women are moving into more combat roles. This puts minority soldiers at risk for being underrepresented in their work units. Tokenism theory predicts that when a work group has less than 15% representation in a social group, the numerically underrepresented minority (i.e., token) members are subject to three disadvantages: higher visibility, informal isolation, and role encapsulation. In the Army, where many companies contain small numbers of women and racial minorities, some soldiers may face additional stressors and constraints. We explored psychosocial, organizational, and health outcomes of all identifiable token women (N = 4,425) and Black soldiers (N = 5,040). Tokens were remarkably similar to non-tokens and majority soldiers on outcomes such as coping skills, adaptability, organizational trust, sleep, substance use, and pain. The intersection of token status in terms of race and gender was not related to any appreciable differences. One potential explanation is the shared Army culture that emphasizes group unity and the importance of the mission above individual characteristics and goals. The Army depends on cohesion, organizational identification, and commitment to the group in order to reduce stress and anxiety, and to maximize combat performance. For soldiers who have internalized this culture, it could be easier to see past individual differences such as gender and race and identify others in the unit as fellow soldiers primarily.     

Finding MAPs using strongly equivalent high order recurrent symmetric connectionist networks

Belief revision is the problem of finding the most plausible explanation for an observed set of evidences. It has many applications in various scientific domains like natural language understanding, medical diagnosis and computational biology. Bayesian Networks (BN) is an important probabilistic graphical formalism widely used for belief revision tasks. In BN, belief revision can be achieved by finding the maximum a posteriori (MAP) assignment. Finding MAP is an NP-Hard problem. In previous work, we showed how to find the MAP assignment in BN using High Order Recurrent Neural Networks (HORN) through an intermediate representation of Cost-Based Abduction. This method eliminates the need to explicitly construct the energy function in two steps, objective and constraints. This paper builds on that previous work by providing the theoretical foundation and proving that the resultant HORN used to find MAP is strongly equivalent to the original BN it tries to solve.