Persistent Mappings in Cross-domain Analogical Learning of Physics Domains
نویسندگان
چکیده
Cross-domain analogies are a powerful method for learning new domains. This paper extends the Domain Transfer via Analogy (DTA) method with the idea of persistent mappings, correspondences between domains that are incrementally built up as a system gains experience with a new domain. We evaluate DTA plus persistent mappings by learning three domains (rotational mechanics, electricity, and heat) by analogy with linear mechanics, showing that persistent mappings improves performance.
منابع مشابه
Exploiting persistent mappings in cross-domain analogical learning of physical domains
Article history: Received 6 July 2011 Received in revised form 9 November 2012 Accepted 13 November 2012 Available online 15 November 2012
متن کاملNORTHWESTERN UNIVERSITY Using Analogy to Overcome Brittleness in AI Systems A DISSERTATION SUBMITTED TO THE GRADUATE SCHOOL IN PARTIAL FULFILLMENT OF THE REQUIREMENTS for the degree DOCTOR OF PHILOSOPHY Field of Computer Science By
Using Analogy to Overcome Brittleness in AI Systems Matthew Evans Klenk One of the most important aspects of human reasoning is our ability to robustly adapt to new situations, tasks, and domains. Current AI systems exhibit brittleness when faced with new situations and domains. This work explores how structure mapping models of analogical processing allow for the robust reuse of domain knowled...
متن کاملUsing Analogy to Overcome Brittleness in AI Systems
Using Analogy to Overcome Brittleness in AI Systems Matthew Evans Klenk One of the most important aspects of human reasoning is our ability to robustly adapt to new situations, tasks, and domains. Current AI systems exhibit brittleness when faced with new situations and domains. This work explores how structure mapping models of analogical processing allow for the robust reuse of domain knowled...
متن کاملDeep Unsupervised Domain Adaptation for Image Classification via Low Rank Representation Learning
Domain adaptation is a powerful technique given a wide amount of labeled data from similar attributes in different domains. In real-world applications, there is a huge number of data but almost more of them are unlabeled. It is effective in image classification where it is expensive and time-consuming to obtain adequate label data. We propose a novel method named DALRRL, which consists of deep ...
متن کاملAnalogical Learning and Formal Proportions: Definitions and Methodological Issues
Analogical learning is a two-step inference process: (i) computation of a mapping between a new and a memorized situation; (ii) transfer from the known to the unknown situation. This approach requires the ability to search for and exploit such mappings, which are based on the notion of analogical proportions, hence the need to properly define these proportions, and to efficiently implement thei...
متن کامل