We present a novel approach for estimating the intrinsic dimensionality of certain point clouds: we assume that the points are sampled from a manifold M of dimension k , with k << D, and corrupted by D -dimensional noise. When M is linear, one may analyze this situation by SVD: with no noise one would obtain a rank k matrix, and noise may be treated as a perturbation of the covariance matrix. When M is a nonlinear manifold, global SVD may dramatically overestimate the intrinsic dimensionality. We introduce a multiscale version SVD and discuss how one can extract estimators for the intrinsic dimensionality that are highly robust to noise, while require a smaller sample size than current estimators.

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.

In this work an AI/ICT Platform is presented, to develop cognitive networks to cope with a management of a great availability of data and a necessity to dispose of prompt right information, extracted by data. In fact, the better strategic decision arise by a prompt availability of target and effective information. A cognitive network, and in particular an intelligent grid, helps to reach this goal. This intelligent grid allows to integrate many data source to drive analytics which transform data into useful information to support advanced operational control and strategic decision making. To realize an intelligent grid, it is necessary, firstly, capturing Knowledge, transforming data in information and introducing the knowledge in ICT framework and in Real-Time Systems. This is the right way to have a set of target and suitable information by using to take a correct decision, especially in real-time problem. So, in this work XBASE Cognitive Mapping Tool is presented. This tool allows to develop an intelligent grid, to support and “automate” strategic decision and so, to solve, also in real-time, every kind of problems. In particular, an application of this tool is presented, in monitoring of wastewater, the “BATTLE” Project.

LODE is a web tool for children that are novice readers, and is primarily meant for deaf children. It proposes written stories and interactive games for reasoning, globally, on the stories. In this paper, first, we motivate the rationale of LODE, and explain its reasoning games. Then we briefly describe the design of the web client-server architecture of LODE; the server employs a constraint programming system for creating and solving the LODE games in real time. Finally, we concentrate on two evaluations of the latest prototype of LODE: one with hearing novice readers; another one with deaf readers. We conclude by discussing the results of the evaluations, and their implications for LODE.

The challenge of designing a human-level learner is central to creating a computational equivalent of the human mind. It demands the level of robustness and flexibility of learning that is still only available in biological systems. Therefore, it is essential that we better understand at a computational level how biological systems naturally develop their cognitive and learning functions. In recent years, biologically inspired cognitive architectures (BICA) have emerged as a powerful new approach toward gaining this kind of understanding. The impressive success of BICA-2008 was clear evidence of this trend. As the second event in the series, BICA-2009 continues our attack on the challenge, with the overall atmosphere of excitement and promise, brainstorming, and collaboration.

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.

We present an interactive learning method that enables a user to iteratively refine a regression model. The user examines the output of the model, visualized as the vertical axis of a 2D scatterplot, and provides corrections by repositioning individual data points to the correct output level. Each repositioned data point acts as a control point for altering the learned model, using the geometry underlying the data. We capture the underlying structure of the data as a manifold, on which we compute a set of basis functions as the foundation for learning. Our results show that manifold-based interactive learning achieves dramatic improvement over alternative approaches.

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.

The Raven's Progressive Matrices (RPM) test is a commonly used test of general human intelligence. The RPM is somewhat unique as a general intelligence test in that it focuses on visual problem solving, and in particular, on visual similarity and analogy. We are developing a small set of methods for problem solving in the RPM which use propositional, imagistic, and multimodal representations, respectively, to investigate how different representations can contribute to visual problem solving and how the effects of their use might emerge in behavior.

In this paper we describe our vision on how to create a system that acquires moral rules by learning affective meaning of human experiences written on the web.