Since the transfer learning can employ knowledge in relative domains to help the learning tasks in current target domain, compared with the traditional learning it shows the advantages of reducing the learning cost and improving the learning efficiency. Focused on the situation that sample data from the transfer source domain and the target domain have similar distribution, an instance transfer...

Sample complexity and safety are major challenges when learning policies with reinforcement learning for real-world tasks, especially when the policies are represented using rich function approximators like deep neural networks. Model-based methods where the real-world target domain is approximated using a simulated source domain provide an avenue to tackle the above challenges by augmenting re...

—In this paper, a novel multi-source transfer learning method based on multi-similarity ((MS)TL) is proposed. First, we measure the similarities between domains at two levels, i.e., “domain-domain” and “sample-domain”. With the multisimilarities, (MS)TL can explore more accurate relationship between the source domains and the target domain. Then, the knowledge of the source domains is transfer...

the present article begins with an articulation of the significance and relation of ‘query and response’ with both dialogue and its semantic perimeters and discloses the sources of rumi’s thinking about this issue. after this taking a comparative stance, this article briefly explores the background and the significance of query and response, dialogue and dialectic as they relate to both ontolog...

background : cystic fibrosis (cf) is an autosomal recessive disorder chiefly characterized by respiratory and gastrointestinal symptoms. this study investigates whether omega-3 fatty acid affects quality of life in children with cf. materials and methods: this was a single-blind, pilot study undertaken at the cystic fibrosis center of sarvar children hospital, mashhad, iran from march 2009 unti...

NLP tasks are often domain specific, yet systems can learn behaviors across multiple domains. We develop a new multi-domain online learning framework based on parameter combination from multiple classifiers. Our algorithms draw from multi-task learning and domain adaptation to adapt multiple source domain classifiers to a new target domain, learn across multiple similar domains, and learn acros...

We have created an open-source mapping between the SIL’s semantic domains (used for rapid lexicon building and organization for under-resourced languages) and WordNet, the standard resource for lexical semantics in natural language processing. We show that the resources complement each other, and suggest ways in which the mapping can be improved even further. The semantic domains give more gene...

Learning invariant features across domains is of vital importance to unsupervised domain adaptation, where classifiers trained on the training examples (source domain) need to adapt to a different set of test examples (target domain) in which no labeled examples are available. In this paper, we propose a novel approach to find the invariant features in the original space and transfer the knowle...