In this position paper we discuss some general properties involved in high-level cognition in situated agents, and sketch an architecture relating sub-symbolic and symbolic information, in which the notion of perceptual inference plays a central role.

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 successful development of neural prostheses requires an understanding of the neurobiological bases of cognitive processes, i.e., how the collective activity of populations of neurons results in a higher-level process not predictable based on knowledge of the individual neurons and/or synapses alone. We have been studying and applying novel methods for representing nonlinear transformations of multiple spike train inputs (multiple time series of pulse train inputs) produced by synaptic and field interactions among multiple subclasses of neurons arrayed in multiple layers of incompletely connected units.

In this work we introduce a defeasible logic programming recommender server that accepts different types of queries from client agents that can be distributed in remote hosts. We formalize new ways of querying recommender servers containing specific information or preferences, and creating a particular context for the queries. This special type of queries (called contextual queries) allows recommender servers to compute recommendations for any client using its preferences, and will be answered using an argumentative inference mechanism. We focus on a particular implementation of recommended systems that extends the integration of argumentation and recommender systems to a multi-agent setting. Our approach is based on a DeLP-server that can answer queries from agents in remote hosts. Since client agents can consult different domain specific recommender servers, then, multiple configurations of clients and servers can be defined.

Our goal is for an autonomous learning agent to acquire the knowledge that serves as the foundations of common sense from its own experience without outside guidance. This requires the agent to (1) learn the structure of its own sensors and effectors; (2) learn a model of space around itself; (3) learn to move effectively in that space; (4) identify and describe objects, as distinct from the static environment; (5) learn and represent actions for affecting those objects, including preconditions and postconditions, and so on. We will provide examples of progress we have made, and the roadmap we envision for future research.

We propose a generative model for high dimensional data consisting of intrinsically low dimensional clusters that are noisily sampled. The proposed model is a mixture of probabilistic principal surfaces (MiPPS) optimized using expectation maximization. We use a Bayesian prior on the model parameters to maximize the corresponding marginal likelihood. We also show empirically that this optimization can be biased towards a good local optimum by using our prior intuition to guide the initialization phase The proposed unsupervised algorithm naturally handles cases where the data lies on multiple connected components of a single manifold and where the component manifolds intersect. In addition to clustering, we learn a functional model for the underlying structure of each component cluster as a parameterized hyper-surface in ambient noise.This model is used to learn a global embedding that we use for visualization of the entire dataset. We demonstrate the performance of MiPPS in separating and visualizing land cover types in a hyperspectral dataset.

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.

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.

A small consortium of philosophers has begun work on the implications of epistemic networks (Zollman 2008 and forthcoming; Grim 2006, 2007; Weisberg and Muldoon forthcoming), building on theoretical work in economics, computer science, and engineering (Bala and Goyal 1998, Kleinberg 2001; Amaral et. al., 2004) and on some experimental work in social psychology (Mason, Jones, and Goldstone, 2008). This paper outlines core philosophical results and extends those results to the specific question of thresholds. Epistemic maximization of certain types does show clear threshold effects. Intriguingly, however, those effects appear to be importantly independent from more familiar threshold effects in networks.

A peloton is a group of cyclists whose individual and collective energy expenditures are reduced when cyclists ride behind others in zones of reduced air pressure; this effect is known in cycling as ‘drafting’. As an aggregate of biological agents (human), a peloton is a complex dynamical system from which patterns of collective behaviour emerge, including phases and transitions between phases, through which pelotons oscillate. Coupling of cyclists’ energy expenditures when drafting is the basic peloton property from which self-organized collective behaviours emerge. Shown here are equations that model coupling behaviours. Environmental constraints are further parameters that affect peloton dynamics. Phases are defined by thresholds of aggregate energy expenditure; shown here are two different, but consistent, conceptual descriptions of these phase transitions. The first is an energetic model that describes phases in terms of individual, bi-coupled and globally-coupled energy output thresholds that define four observable changes in peloton behaviour. A second, economic model incorporates competition and cooperation dynamics: cooperation increases as power outputs and course constraints increase and population diminishes, and where competition and cooperation for resources results in peloton divisions into sub-pelotons whose average fitness levels are more closely homogeneous.