GLAIR (Grounded Layered Architecture with Integrated Reasoning) is a multi-layered cognitive architecture for embodied agents operating in real,virtual, or simulated environments containing other agents. The highest layer of the GLAIR Architecture, the Knowledge Layer (KL), contains the beliefs of the agent, and is the layer in which conscious reasoning, planning, and act selection is performed. The lowest layer of the GLAIR Architecture, the Sensori-Actuator Layer (SAL), contains the controllers of the sensors and effectors of the hardware or software robot. Between the KL and the SAL is the Perceptuo-Motor Layer (PML), which grounds the KL symbols in perceptual structures and subconscious actions, contains various registers for providing the agent's sense of situatedness in the environment, and handles translation and communication between the KL and the SAL. The motivation for the development of GLAIR has been "Computational Philosophy", the computational understanding and implementation of human-level intelligent behavior without necessarily being bound by the actual implementation of the human mind. Nevertheless, the approach has been inspired by human psychology and biology.

By this paper we would like to open a discussion on the need ofBy this paper we would like to open a discussion on the need of Emotional Intelligence as a feature in machines interacting with humans. However, we restrain from making a statement about the need of emotional experience in machines. We argue that providing machines computable means for processing emotions is a practical need requiring implementation of a set of abilities included in the Emotional Intelligence Framework. We introduce our methods and present the results of some of the first experiments we performed in this matter.

Thought is an essential aspect of mental function, but remains very poorly understood. In this paper, we take the view that thought is a response process — the emergent and dynamic configuration of structured response, i.e., ideas, by composing response elements, i.e., concepts, from a repertoire under the influence of afferent information, internal modulation and evaluative feedback. We hypothesize that the process of generating ideas occurs at two levels: 1) The identification of a context-specific subset — or workspace — of concepts from the larger repertoire; and 2) The configuration of plausible/useful ideas within this workspace. Workspace configuration is mediated by a dynamic selector network (DSN), which is an internal attention/working memory system. Each unit of the DSN selectively gates a subset of concepts, so that any pattern of activity in the DSN defines a workspace. The configuration of efficient and flexible workspaces is mediated by dynamical structures termed graded attractors — attractors where the set of active units can be varied in systematic order by inhibitory modulation. A graded attractor in the DSN can project a selective bias — a ``searchlight" — onto the concept repertoire to define a specific workspace, and inhibitory modulation can be used to vary the breadth of this workspace. As it experiences various contexts, the cognitive system can configure a set of graded attractors, each covering a domain of similar contexts. In this paper, we focus on a mechanism for configuring context-specific graded attractors, and evaluate its performance over a set of contexts with varying degrees of similarity. In particular, we look at whether contexts are clustered appropriately into a minimal number of workspaces based on the similarity of the responses they require. While the focus in this paper is on semantic workspaces, the model is broadly applicable to other cognitive response functions such as motor control or memory recall.

This extended abstract outlines my invited keynote presentation of the recent work on neuromorphic networks ("CrossNets") based on hybrid CMOS/nanoelectronic ("CMOL") circuits, in the space-saving Q/A format.

The concept of 'self' has been investigated using many methodologies (e.g. the philosophical approach and the neurobiological approach) that has given rise to issues that yielded popular debates. In this paper, I endeavor to employ virtual reality as a new tool for investigating 'self'. Future directions are provided that could be further helpful in advancing our understanding about the self amidst the complexity of culture.

A self-organizing neural network is described that can associate between different modalities and also has the ability to learn perceptual sequences. This architecture is a step towards the development of a complete agent containing simplified versions of all major neural subsystems in a mammal. It aims at exploring as well as takes inspiration from the idea that cognitive function involves an internal simulation of perception and movement. We have tested the architecture in simulations as well as together with real sensors with very encouraging results.

A neural cognitive architecture would be an architecture based on simulated neurons, that provided a set of mechanisms for all cognitive behaviour. Moreover, this would be compatible with biological neural behaviour. As a result, such architectures can both form the basis of a fully-fledged AI and help to explain how cognition emerges from a collection of neurons in the human brain. The development of such a neural cognitive architecture is in its infancy, but a proto-architecture in the form of behaving agents entirely based on simulated neurons is described. These agents take natural language commands, view the environment, plan and act. The development of these agents has led to a series of questions that need to be addressed to advance the development of neural cognitive architectures. These questions include long posed ones where progress has been made, such as the binding and symbol grounding problems; issues about biological architectures including neural models and brain topology; issues of emergent behaviour such as short and long-term Cell Assembly dynamics; and issues of learning such as the stability-plasticity dilemma. These questions can act as a road map for the development of neural cognitive architectures and AIs based on them.

The brain's ability to do this in a self-stabilizing fashion employs several different types of predictive mechanisms. The lack of a single such mechanism is clarified by accumulating theoretical and empirical evidence that brain specialization is governed by computationally complementary processing streams. The present talk will discuss recent progress towards explaining fundamental brain processes such as 3D vision in natural scenes; opticflow based navigation in natural scenes towards goals around obstacles and spatial navigation in the dark; object and scene learning, recognition, and search; cognitiveemotional dynamics that direct motivated attention towards valued goals; adaptive sensory-motor control circuits, such as those that coordinate predictive smooth pursuit and saccadic eye movements; and planning circuits that temporarily represent sequences of events in working memory and learn sequential plans, including repeated events or actions. These competences clarify the global system-level organization as well as the local microcircuit level organization of many brain systems, ranging from form and motion streams in the visual cortex through inferotemporal and parietal cortex, perirhinal and parahippocampal cortex; supplementary and frontal eye fields; orbitofrontal, ventrolateral, and dorsolateral prefrontal cortex; entorhinal and hippocampal cortex; and subcortical areas including basal ganglia, amygdala, superior colliculus, and nucleus reticularis tegmenti pontis. These model systems are being transferred as they become ready to a wide variety of large-scale applications in technology.

This paper claims for a shift towards "the formal sciences" in the cognitive sciences. In order to explain the phenomenon of cognition, including aspects such as learning and intelligence, it is necessary to explore the concepts and methodologies offered by the formal sciences. In particular, category theory is proposed as the most fitting tool for the building of an unified theory of cognition. This paper proposes a radically new view based in category theory is provided. A cognitive model is informally defined as a mapping between two different structures, while a structure is the set of components of a system and their relationships. Put formally in categorical terms, a model is a functor between categories that reflects the structural invariance between them. In the paper, the theory of categories is presented as the best possible framework to deal with complex system modeling -ie: biologically inspired systems that transcend and offer a much more powerful tool kit to deal with the phenomenon of cognition that other purely verbal tools like the psychological categories that Rosch or Harnad refer.

A novel analytical methodology has proven fruitful in developing a functional identification of consciousness with operable mental control structure in human higher brain function. Two operational homologies (one associated with language, the other tool use) derived from mammalian instrumental behavioral competence are identified, each exadaptively accessible: one a specialization of attentive search to (conventional, linguistic) internalized symbolic lexicon; the second being a combination – a co-parallel activation – of symbolically specialized attention with the original external ‘spotlight’ in order to support (deliberative, choice-making) navigational tasking. The mechanism by which consciousness becomes articulated to support the specialized control requirements of three cognitive performance levels is described, in particular for the case of the social bipedal hominid. A single articulated template model is posed to intervene between the incoherent neuronal and the coherently conscious mental level of higher brain operation. This cognitive system theory logic lends itself to an explanation of the exadaptive acquisition of a cognitively objectifiable self-model from within subjective experience, and a plausible heuristic for the systematic building of self-aware mental repertoire is discovered.