A deeply-interactive hybrid neural-symbolic cognitive architecture is defined as one in which the neural-net and symbolic components interact frequently and dynamically, so that each intervenes significantly in the other's internal operations, and the two form a combined dynamical system at the time-scale of each component's individual cognitive operations.  An example architecture of this nature that is currently under development is described: OpenCog NS, based on integration of the OpenCog cognitive architecture (which incorporates symbolic, evolutionary and connectionist aspects) with a hierarchical attractor neural network (HANN).  In this integrated architecture, the neural and non-neural aspects each play major roles, and the depth of the interconnection is revealed for example in the facts that symbolic reasoning intervenes in the process of attractor formation within the HANN, whereas the HANN plays a major role in guiding the individual steps of logical inference and evolutionary program learning processes.

This paper argues that supervised cognitive growth in artifacts will be very difficult to achieve without detailed knowledge about systems’ internal states. Physical information is too low level to provide a useful understanding of a system’s behavior, and it is more pragmatically useful to take a mental stance towards an artificial system and interpret its actions in terms of mental states. This mental stance is similar to Dennett’s intentional stance, except the ascription of beliefs and rationality in the intentional stance is replaced by the attribution of low level mental states in the mental stance. In some cases it might also be useful to take a conscious stance towards an artificial system that interprets its behavior as the outcome of a conscious decision making process. Since most artifacts lack language, automatic analysis techniques have to be used to identify the contents of their minds, and the second half of this paper suggests how some of the earlier work of Aleksander and Atlas can be applied in this area.

Many biological models of human motivation and behavior posit a functional division between those subsystems respon- sible for approach and avoidance behaviors. Gray and McNaughton's (2000) revised Reinforcement Sensitivity Theory (RST) casts this distinction in terms of a Behavioral Activation System (BAS) and a Fight-Flight-Freeze System (FFFS), mediated by a third, conflict resolution system — the Behavioral Inhibition System (BIS). They argued that these are fundamental, functionally distinct systems. The model has been highly influential both in personality psychology, where it provides a biologically-based explanation of traits such as extraversion and neuroticism, and in clinical psychology wherein state disorders such as Major Depressive Disorder and Generalized Anxiety Disorder can be modeled as differences in baseline sensitivities of one or more of the systems. In this paper, we present work in progress on implementing a simplified simulation of RST in a set of embodied virtual characters. We argue that RST provides an interesting and potentially powerful starting point for cognitive architectures for various applications, including interactive entertainment, in which simulation of human-like affect and personality is important.

This paper presents a system for advanced verbal interactions between humans and artificial agents with the aim to learn a simple language in which words and their meaning are grounded in sensory-motor experiences of the agent, and which allows agents to interact and cooperate with humans in shared environments. The system learns grounded language models from examples with a minimum of user intervention and without feedback, and it has been used to understand and subsequently to generate appropriate natural language descriptions of real objects and to engage in verbal interactions with a human partner.

In the past years we developed several design processes (Chella et Perception, also including memory, is one of the most important al. 2006)(Cossentino and Seidita 2004)(Cossentino, Gaglio, features a robotic system must present. In (Chella and Seidita) following the approach based on Situational and Manzotti 2007) it is argued that a perception process can Method Engineering paradigm we fixed in these years be modelled and implemented as a continuous interaction (Cossentino et al. 2007)(Seidita et al. 2009). In the following loop among brain, body and environment; by continuously subsections an overview on the used SME approach, comparing actual and expected "data" coming from the environment the PASSI design process, and the robot perception loop will the robot achieves the ability to gain perceptual be given.

Consciousness is a major feature of mammalian nervous systems. Recent evidence indicates it may extend from mammals to birds and even cephalopods (Edelman, Seth 2009). Since all major biological adaptations are functional, or sequelae of biofunctions, and since brains perform computations, it would seem that consciousness must have a basic biocomputational function. Biologically, that means of course that consciousness endows nervous systems with one or more adaptive advantages leading to higher gene frequencies for those brains. Given that mammals have existed for some 200 million years, and that mammals share the thalamocortical core that supports conscious states, it is very likely that conscious brains have gathered not just one but many biocomputational functions. That certainly accords with our common sense notions of conscious (as well as unconscious) activities.

Many aspects can be taken into account in order to assess the power and potential of a cognitive architecture. In this paper we argue that ConsScale, a cognitive scale inspired on the development of consciousness, can be used to characterize and evaluate cognitive architectures from the point of view of the effective integration of their cognitive functionalities. Additionally, a graphical characterization of the cognitive power of artificial agents is proposed as a helpful tool for the analysis and comparison of Machine Consciousness implementations. This is illustrated with the application of the scale to a particular problem domain in the context of video game synthetic bots.

In discussions about the physical support of conscious experience, a recent trend has been introduced (by Tononi and various colleagues) that measures the capacity of a network to discriminate among different states and integrate the information generated by this discrimination. This capacity to generate and integrate information can be used to understand the information processing in a network and Tononi has claimed that it is also linked to conscious experience. This paper describes experiments in which networks of weightless neurons were used to explore how different connection patterns and architectures affected the effective information generated by a network. The training of these networks using easily recognizable images made it easy to monitor their internal states, and this supports the interpretation of the system using the mental stance, which is described in a companion paper. By applying the same training to different architectures we were also able to study how the informational relationships depended on a combination of training and other dynamic effects.

Inferring causal relations by analyzing statistical dependences among observed random variables is a challenging task if no controlled randomized experiments are available. Socalled constraint-based approaches to causal discovery (Pearl, 2000; Spirtes et al., 1993) select among all directed acyclic graphs (DAGs) those that satisfy the Markov condition and the faithfulness assumption, i.e., those for which the observed independences are imposed by the structure rather than being a result of specific choices of parameters of the Bayesian network. These approaches are unable to distinguish among causal DAGs that impose the same independences. In particular, it is impossible to distinguish between X Y and Y X. More recently, several methods have been suggested that use not only conditional independences, but also more sophisticated properties of the joint distribution. For simplicity, we explain the ideas for the two variable setting since this case is particularly challenging. Kano & Shimizu (2003) use models Y f(X) N (1) where f is a linear function and N is additive noise that is independent of the hypothetical cause X. This is an example for an additive noise model from X to Y. Apart from trivial

The identification of performance-optimizing parameter settings is an important part of the development and application of algorithms. We describe an automatic framework for this algorithm configuration problem. More formally, we provide methods for optimizing a target algorithms performance on a given class of problem instances by varying a set of ordinal and/or categorical parameters. We review a family of local-search-based algorithm configuration procedures and present novel techniques for accelerating them by adaptively limiting the time spent for evaluating individual configurations. We describe the results of a comprehensive experimental evaluation of our methods, based on the configuration of prominent complete and incomplete algorithms for SAT. We also present what is, to our knowledge, the first published work on automatically configuring the CPLEX mixed integer programming solver. All the algorithms we considered had default parameter settings that were manually identified with considerable effort. Nevertheless, using our automated algorithm configuration procedures, we achieved substantial and consistent performance improvements.