In this paper, we present a new approach to Transfer Learning (TL) in Reinforcement Learning (RL) for cross-domain tasks. Many of the available techniques approach the transfer architecture as a method of speeding up the learning target task. We propose to adapt and reuse the mapped source task optimal-policy directly in related domains. We show the optimal policy from a related source task can...

Domain adaptation is an important technology to handle domain dependence problem in sentiment analysis field. Existing methods usually rely on sentiment classifiers trained in source domains. However, their performance may heavily decline if the distributions of sentiment features in source and target domains have significant difference. In this paper, we propose an active sentiment domain adap...

domain ΩT domain ΩS "well-separated" xi yi Specifically, let’s say we have domains ΩS of N source points and ΩT of M target points, and these domains are “well-separated” (we will formalize this in section 3). Our goal is to compute the influence of all source points onto target points. Let the M × N matrix [K]ij = K(xi, yj) and assume it is approximately low-rank, so that K ≈ UV T with U of si...

We consider the transfer learning scenario, where the learner does not have access to the source domain directly, but rather operates on the basis of hypotheses induced from it – the Hypothesis Transfer Learning (HTL) problem. Particularly, we conduct a theoretical analysis of HTL by considering the algorithmic stability of a class of HTL algorithms based on Regularized Least Squares with biase...

This contribution studies a feature extraction technique aiming at reducing differences between domains in image classification. The purpose is to find a common feature space between labeled samples issued from a source image and test samples belonging to a related target image. The presented approach, Transfer Component Analysis, finds a transformation matrix performing a joint mapping of the ...

An integral domain $D$ is called a emph{locally GCD domain} if $D_{M}$ is aGCD domain for every maximal ideal $M$ of $D$. We study somering-theoretic properties of locally GCD domains. E.g., we show that $%D$ is a locally GCD domain if and only if $aDcap bD$ is locally principalfor all $0neq a,bin D$, and flat overrings of a locally GCD domain arelocally GCD. We also show that the t-class group...

In this era of big data, Multi-source Domain Adaptation (MDA) becomes more and popular is employed to make full use available source data collected from several different, but related domains. Although multiple domains provide much information, the processing domain shifts challenging, especially in learning a common domain-invariant representation for all Moreover, it counter-intuitive treat e...

This paper argues that there need not be a full correspondence between source and target domains when interpreting metaphors. Instead, inference is performed in the source domain, and conclusions transferred to the target. A description of a computer system, ATT-Meta, that partially implements these ideas is provided.

A surface-shrinking algorithm is demonstrated for automated source position localization one scattering depth into discretized simulation domains, in near-infrared imaging. The algorithm allows users to accurately place source fiber locations with minimal guidance. OCIS codes: (100.0100) Image Processing; (100.3010) Image Reconstruction Techniques