Search results for "Intelligence"
showing 10 items of 6959 documents
Imitation Learning and Anchoring through Conceptual Spaces
2007
In order to have a robotic system able to effectively learn by imitation and not merely reproduce the movements of a human teacher, the system should have the capability to deeply understand the perceived actions to be imitated. This paper deals with the development of a cognitive architecture for learning by imitation in which a rich conceptual representation of the observed actions is built. The purpose of the following discussion is to show how the same conceptual representation can be used both in a bottom-up approach, in order to learn sequences of actions by imitation learning paradigm, and in a top-down approach, in order to anchor the symbolical representations to the perceptual act…
A cognitive architecture for music perception exploiting conceptual spaces
2015
A cognitive architecture for a musical agent is presented. The architecture extends and complete an architecture for computer vision previously developed by the author by taking into account many relationships between vision and music perception. The focus of the agent architecture is an intermediate conceptual area between the subconceptual and linguistic areas. A conceptual space for the perception of tones and intervals is thus presented, based on the dissonance measure of the tones. Problems and future works of the proposed approach are finally discussed.
The Prefrontal Cortex and Neurological Impairments of Active Thought
2018
This article reviews the effects of lesions to the frontal cortex on the ability to carry out active thought, namely, to reason, think flexibly, produce strategies, and formulate and realize plans. We discuss how and why relevant neuropsychological studies should be carried out. The relationships between active thought and both intelligence and language are considered. The following basic processes necessary for effective active thought are reviewed: concentration, set switching, inhibiting potentiated responses, and monitoring and checking. Different forms of active thought are then addressed: abstraction, deduction, reasoning in well-structured and ill-structured problem spaces, novel st…
Cloning and training collective intelligence with generative adversarial networks
2021
Industry 4.0 and highly automated critical infrastructure can be seen as cyber‐physical‐social systems controlled by the Collective Intelligence. Such systems are essential for the functioning of the society and economy. On one hand, they have flexible infrastructure of heterogeneous systems and assets. On the other hand, they are social systems, which include collaborating humans and artificial decision makers. Such (human plus machine) resources must be pre‐trained to perform their mission with high efficiency. Both human and machine learning approaches must be bridged to enable such training. The importance of these systems requires the anticipation of the potential and previously unknow…
From Metaphors to Simulations to Idioms: Supporting the Conceptualisation Process
2004
The concept of metaphor has been used in UI design in a loose manner. There is a need to conceptually separate it from related concepts to restore the power it used to have in rhetoric. It is also important to understand the life cycle of metaphor, how it changes over time in the conceptualisation process. This is especially topical in ubiquitous computing, in which entirely new concepts and interaction styles are introduced. In this paper, we describe the use of metaphors and related concepts in theory and apply the approach in a mobile application.
Knowledge representation for robotic vision based on conceptual spaces and attentive mechanisms
1995
A new cognitive architecture for artificial vision is proposed. The architecture is aimed for an autonomous intelligent system, as several cognitive hypotheses have been postulated as guidelines for its design. The design is based on a conceptual representation level between the subsymbolic level processing the sensory data, and the linguistic level describing scenes by means of a high-level language. The architecture is also based on the active role of a focus of attention mechanism in the link between the conceptual and the linguistic level. The link between the conceptual level and the linguistic level is modelled as a time-delay attractor neural network.
Perceptual semantics: A three-level approach
2010
In this work we suggest a model according to which semantics has been already generated during the perception through the interaction of three dynamic levels of perceptual organization. We consider perceptual grouping as the first order processing. Shape formation is considered as the second order processing. Both grouping and shape formation can be considered as two complementary and interrelated processes of perceptual organization. The third — partially overlapping — level is meaning assignment. Most of the results are supported by empirical evidence based on new visual illusions of shape and meaning and are consistent with several other proposals (e.g., [1], [2] and [3]).
Towards a conceptual representation of actions
2000
An autonomous robot involved in missions should be able to generate, update and process its own actions. It is not plausible that the meaning of the actionsus ed by the robot isgiv en form the outside of the system itself. Rather, this meaning should be anchored to the world through the perceptual abilitiesof the robot. We present an approach to conceptual action representation based on a "conceptual" level that actsasan intermediate level between symbolsand data coming form sensors. Symbolic representations are interpreted by mapping them on the conceptual level through a mapping mechanism based on artificial neural networks.
AGI and Machine Consciousness
2012
This review discusses some of main issues to be addressed to design a conscious AGI agent: the agent’s sense of the body, the interaction with the environment, the agent’s sense of time, the free will of the agent, the capability for the agent to have some form of experience, and finally the relationship between consciousness and creativity.
The Argument Dependency Model
2015
This chapter summarizes the architecture of the extended Argument Dependency Model (eADM), a model of language comprehension that aspires toward neurobiological plausibility. It combines design principles from neurobiology with insights on cross-linguistic diversity. Like other current models, the eADM posits that auditory language processing proceeds along two distinct streams in the brain emanating from auditory cortex: the antero-ventral and postero-dorsal streams. Both streams are organized hierarchically and information processing takes place in a cascaded fashion. Each stream has functionally unified computational properties congruent with its role in primate audition. While the dorsa…