Learning Łukasiewicz logic

The integration between connectionist learning and logic-based reasoning is a longstanding foundational question in artificial intelligence, cognitive systems, and computer science in general. Research into neural-symbolic integration aims to tackle this challenge, developing approaches bridging the gap between sub-symbolic and symbolic representation and computation. In this line of work the core method has been suggested as a way of translating logic programs into a multilayer perceptron computing least models of the programs. In particular, a variant of the core method for three valued Łukasiewicz logic has proven to be applicable to cognitive modelling among others in the context of Byrne’s suppression task. Building on the underlying formal results and the corresponding computational framework, the present article provides a modified core method suitable for the supervised learning of Łukasiewicz logic (and of a closely-related variant thereof), implements and executes the corresponding supervised learning with the backpropagation algorithm and, finally, constructs a rule extraction method in order to close the neural-symbolic cycle. The resulting system is then evaluated in several empirical test cases, and recommendations for future developments are derived.     

Turing redux: Enculturation and computation

Many of our cognitive capacities are shaped by enculturation. Enculturation is the acquisition of cognitive practices such as symbol-based mathematical practices, reading, and writing during ontogeny. Enculturation is associated with significant changes to the organization and connectivity of the brain and to the functional profiles of embodied actions and motor programs. Furthermore, it relies on scaffolded cultural learning in the cognitive niche. The purpose of this paper is to explore the components of symbol-based mathematical practices. Phylogenetically, these practices are the result of concerted organism-niche interactions that have led from approximate number estimations to the emergence of discrete, symbol-based mathematical operations. Ontogenetically, symbol-based mathematical practices are associated with plastic changes to neural circuitry, action schemata, and motor programs. It will be suggested that these practices rely on previously acquired capacities such as subitizing and counting. With these considerations in place, I will argue that computations, understood in the sense of Turing (1936), are a specific kind of symbol-based mathematical practices that can be realized by human organisms, machines, or by hybrid organism-machine systems. In sum, this paper suggests a new way to think about mathematical cognition and computation.     

Hierarchies of Self-Organizing Maps for action recognition

We propose a hierarchical neural architecture able to recognise observed human actions. Each layer in the architecture represents increasingly complex human activity features. The first layer consists of a SOM which performs dimensionality reduction and clustering of the feature space. It represents the dynamics of the stream of posture frames in action sequences as activity trajectories over time. The second layer in the hierarchy consists of another SOM which clusters the activity trajectories of the first-layer SOM and learns to represent action prototypes. The third- and last-layer of the hierarchy consists of a neural network that learns to label action prototypes of the second-layer SOM and is independent – to certain extent – of the camera’s angle and relative distance to the actor. The experiments were carried out with encouraging results with action movies taken from the INRIA 4D repository. In terms of representational accuracy, measured as the recognition rate over the training set, the architecture exhibits 100% accuracy indicating that actions with overlapping patterns of activity can be correctly discriminated. On the other hand, the architecture exhibits 53% recognition rate when presented with the same actions interpreted and performed by a different actor. Experiments on actions captured from different view points revealed a robustness of our system to camera rotation. Indeed, recognition accuracy was comparable to the single viewpoint case. To further assess the performance of the system we have also devised a behavioural experiments in which humans were asked to recognise the same set of actions, captured from different points of view. Results form such a behavioural study let us argue that our architecture is a good candidate as cognitive model of human action recognition, as architectural results are comparable to those observed in humans.     

Life span changes: Performing a continuous 1:2 bimanual coordination task

The experiment was conducted to determine the influence of mirror movements in bimanual coordination during life span. Children, young adults, and older adults were instructed to perform a continuous 1:2 bimanual coordination task by performing flexion–extension wrist movements over 30 s where symmetrical and non-symmetrical coordination patterns alternate throughout the trial. The vision of the wrists was covered and Lissajous-feedback was provided online. All age groups had to perform 10 trials under three different load conditions (0 kg, .5 kg, 1.0 kg: order counterbalanced). Load was manipulated to determine if increased load increases the likelihood of mirror movements. The data indicated that the performance of the young adults was superior compared to the children and older adults. Children and older adults showed a stronger tendency to develop mirror movements and had particular difficulty in performing the non-symmetrical mode. This type of influence may be attributed to neural crosstalk.     

Biologically Plausible,Human‐Scale Knowledge Representation

Several approaches to implementing symbol‐like representations in neurally plausible models have been proposed. These approaches include binding through synchrony (Shastri & Ajjanagadde, 1993 ), “mesh” binding (van der Velde & de Kamps, 2006 ), and conjunctive binding (Smolensky, 1990 ). Recent theoretical work has suggested that most of these methods will not scale well, that is, that they cannot encode structured representations using any of the tens of thousands of terms in the adult lexicon without making implausible resource assumptions. Here, we empirically demonstrate that the biologically plausible structured representations employed in the Semantic Pointer Architecture (SPA) approach to modeling cognition (Eliasmith, 2013 ) do scale appropriately. Specifically, we construct a spiking neural network of about 2.5 million neurons that employs semantic pointers to successfully encode and decode the main lexical relations in WordNet, which has over 100,000 terms. In addition, we show that the same representations can be employed to construct recursively structured sentences consisting of arbitrary WordNet concepts, while preserving the original lexical structure. We argue that these results suggest that semantic pointers are uniquely well‐suited to providing a biologically plausible account of the structured representations that underwrite human cognition.     

Pure word deafness and the bilateral processing of the speech code

The analysis of pure word deafness (PWD) suggests that speech perception, construed as the integration of acoustic information to yield representations that enter into the linguistic computational system, (i) is separable in a modular sense from other aspects of auditory cognition and (ii) is mediated by the posterior superior temporal cortex in both hemispheres. PWD data are consistent with neuropsychological and neuroimaging evidence in a manner that suggests that the speech code is analyzed bilaterally. The typical lateralization associated with language processing is a property of the computational system that acts beyond the analysis of the input signal. The hypothesis of the bilateral mediation of the speech code does not imply that both sides execute the same computation. It is proposed that the speech signal is asymmetrically analyzed in the time domain, with left‐hemisphere mechanisms preferentially extracting information over shorter (25–50 ms) temporal integration windows and right mechanisms over longer (150–250 ms) windows.     

Understanding the emergence of modularity in neural systems

Modularity in the human brain remains a controversial issue, with disagreement over the nature of the modules that exist, and why, when, and how they emerge. It is a natural assumption that modularity offers some form of computational advantage, and hence evolution by natural selection has translated those advantages into the kind of modular neural structures familiar to cognitive scientists. However, simulations of the evolution of simplified neural systems have shown that, in many cases, it is actually non-modular architectures that are most efficient. In this paper, the relevant issues are discussed and a series of simulations are presented that reveal crucial dependencies on the details of the learning algorithms and tasks that are being modelled, and the importance of taking into account known physical brain constraints, such as the degree of neural connectivity. A pattern is established which provides one explanation of why modularity should emerge reliably across a range of neural processing tasks.     

The neural network model of organizational identification

This paper proposes the Neural Network Model of Organizational Identification; the model depicts organizational identification as an associative link within an organization member’s social knowledge structure of self as it relates to a focal organization. Within this knowledge structure, organization identification connects self to organization via an attribute sub-network that includes self-concept and organization identity and via a valance sub-network that includes organization based self-esteem and attitudinal commitment. This model draws on the principles of balance-congruity, imbalance dissonance, and differentiation [Greenwald, A. G., Banaji, M. R., Rudman, L. A., Farnham, S. D., Nosek, B. A., & Mellott, D. S. (2002). A unified theory of implicit attitudes, stereotypes, self-esteem, and self-concept. Psychological Review, 109, 3–25.] to predict relationships between these organizational constructs. The Neural Network Model of Organizational Identification is parsimonious yet it effectively integrates and synthesizes the burgeoning literature on organizational identification. By operating at a neural network level of analysis, the model departs substantially from existing organization models by (1) specifying unique construct definitions; (2) offering an alternative perspective of the affective/cognitive dimensions and interrelationships; (3) introducing the concept of implicit cognition to the literature on organizational identification, which makes apparent problems with current measures; and (4) explaining phenomena not explained in existing models. This perspective adds precision and reveals that organizational identification is interconnected within a reciprocal network of mutual causality.     

The self-regulating brain: Cortical-subcortical feedback and the development of intelligent action

To speak of cognitive regulation versus emotion regulation may be misleading. However, some forms of regulation are carried out by executive processes, subject to voluntary control, while others are carried out by “automatic” processes that are far more primitive. Both sets of processes are in constant interaction, and that interaction gives rise to a stream of activity that is both cognitive and emotional. Studying the brain helps us understand these reciprocal regulatory influences in some detail. Cortical activities regulate subcortical activities through executive modulation of prepotent appraisals and emotional responses. Subcortical systems regulate the cortex by tuning its activities to the demands or opportunities provided by the environment. Cortical controls buy us time, as needed for planning and intelligent action. Subcortical controls provide energy, focus, and direction, as needed for relevant emotion-guided behaviour. We review the neural processes at work in both directions of regulatory activity, looking at the anterior cingulate cortex (ACC) as a hub of cortical systems mediating downward control, and discussing limbic, hypothalamic, and brainstem systems that mediate upward control. A macrosystem that displays both directions of control includes the ACC and the amygdala within a feedback circuit whose features vary with clinical-personality differences. Developmental changes in ACC-mediated self-regulation support advances in directed attention, response inhibition, and self-monitoring. Developmental changes in amygdala-mediated self-regulation involve the compilation of meanings that direct thought and behaviour, thus consolidating individual differences over the lifespan. In this way, the capacity to exert voluntary control develops alongside the accumulation of associations that trigger the responses that demand control. The balance between these developmental progressions has implications for personality formation and mental health.