The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Inspired by the work on sensory substitution which shows the technical and practical possibilities for perceptual learning, we have carried out a global longitudinal study of the learning capacities for reading digital graphical objects by four blind high-school students. We report here the results obtained with the Tactos system during certain phases of this study, in particular the acquisition of...
Demonstration learning is a powerful and practical technique to develop robot behaviors. Even so, development remains a challenge and possible demonstration limitations can degrade policy performance. This work presents an approach for policy improvement and adaptation through a tactile interface located on the body of a robot. We introduce the Tactile Policy Correction (TPC) algorithm, that employs...
Acquiring concepts from experience is a key aspect of development and one that is commonly neglected in learning agents. In this work, concept acquisition is formulated as an unsupervised learning problem and is addressed with a novel algorithm: kx-trees. kx-trees differ from prior approaches to unsupervised learning in that they require very little information; four user selected parameters determine...
This article presents a mechanism for the early development of imitation through a simulation of infant-caregiver interaction. A model was created to acquire a body mapping (a mapping from observed body motions to motor commands), which is necessary for imitation, while discriminating self-motion from the motion of the other. The simulation results show that the development of a body mapping depends...
In this paper we present a computational model for incremental word meaning acquisition. It is designed to rapidly build category representations which correspond to the meaning of words. In contrast to existing approaches, our model further extracts word meaning-relevant features using a statistical learning technique. Both category learning and feature extraction are performed simultaneously. To...
Psychological research has demonstrated that subjects shown animations consisting of nothing more than simple geometric shapes perceive the shapes as being alive, having goals and intentions, and even engaging in social activities such as chasing and evading one another. While the subjects could not directly perceive affective state, motor commands, or the beliefs and intentions of the actors in the...
An intelligent agent, embedded in the physical world, will receive a high-dimensional ongoing stream of low-level sensory input. In order to understand and manipulate the world, the agent must be capable of learning high-level concepts. Object is one such concept. We are developing the Object Semantic Hierarchy (OSH), which consists of multiple representations with different ontologies. The OSH factors...
In this paper we investigate a computational model of word learning, that is embedded in a cognitively and ecologically plausible framework. Multi-modal stimuli from four different speakers form a varied source of experience. The model incorporates active learning, attention to a communicative setting and clarity of the visual scene. The model's ability to learn associations between speech utterances...
It has been a puzzle how the syntax of natural language could be learned from positive evidence alone. Here we present a hybrid neural-network model in which artificial syntactic categories are acquired through unsupervised competitive learning due to grouping together lexical words with consistent phonological endings. These relatively large syntactic categories then become target signals for a feed-forward...
“Gain-Based Separation” is a novel heuristic that modifies the standard multiclass decision tree learning algorithm to produce forests that can describe an example or object with multiple classifications. When the information gain at a node would be higher if all examples of a particular classification were removed, those examples are reserved for another tree. In this way, the algorithm performs...
In this paper we address the question of how closely everyday human teachers match a theoretically optimal teacher. We present two experiments in which subjects teach a concept to our robot in a supervised fashion. In the first experiment we give subjects no instructions on teaching and observe how they teach naturally as compared to an optimal strategy. We find that people are suboptimal in several...
How can autonomous agents with access to only their own sensory-motor experiences learn to look at visual targets? We explore this seemingly simple question, and find that naïve approaches are surprisingly brittle. Digging deeper, we show that learning to look at visual targets contains a deep, rich problem structure, relating sensory experience, motor experience, and development. By capturing this...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.