Toward Interactive Relational Learning
نویسندگان
چکیده
This paper introduces the Interactive Relational Machine Learning (iRML) paradigm in which users interactively design relational models by specifying the various components, constraints, and relational data representation, as well as perform evaluation, analyze errors, and make adjustments and refinements in a closed-loop. iRML requires fast real-time learning and inference methods capable of interactive rates. Methods are investigated that enable direct manipulation of the various components of the RML method. Visual representation and interaction techniques are also developed for exploring the space of relational models and the trade-offs of the various components and design choices.
منابع مشابه
Relational Concept Learning via Guided Interactive Discovery
A key goal in both education and higher-order cognition research is to understand how relational concepts are best learned. In the current work, we present a novel approach for learning complex relational categories – a low-support, interactive discovery interface. The platform, which allows learners to make modifications to exemplars and see the corresponding effects on membership, holds the p...
متن کاملTowards Interactive Relational Reinforcement Learning of Concepts
We present a framework for the interactive machine learning of denotational concept semantics in communication between humans and artificial agents. The capability of software agents and robots to learn how to communicate verbally with human users is obviously highly useful in several real-world applications. Whereas the large majority of existing approaches to the machine learning of word sens...
متن کاملImagery as a Relational Organizer in Associative Learning 1
Mental imagery improves paired-associate (PA) learning relative to overt rehearsal. The effect might be due to increased reliability of stimulus encoding or to increased relational association produced by imagery. These hypotheses expect different outcomes when imagery and rote-rehearsal Ss are compared on memory tests of stimulus recognition and on recall of the response term conditional upon ...
متن کاملInteractive Relational Reinforcement Learning of Concept Semantics (Extended Abstract)
We propose a novel approach to the machine learning of formal word sense, learned in interaction with human users using a new form of Relational Reinforcement Learning. The envisaged main application area of our framework is humanmachine communication, where a software agent or robot needs to understand concepts used by human users (e.g., in Natural Language Processing, HCI or Information Retri...
متن کامل