We studied transfer of learning across two games of strategic interaction. We found that the interpersonal relation between two players during and across two games influence development of reciprocal trust and transfer of learning from one game to another. We show that two types of similarities between the games affect transfer: (1) deep similarities facilitate transfer of an optimal solution a...

In transfer learning the aim is to solve new learning tasks using fewer examples by using information gained from solving related tasks. Existing transfer learning methods have been used successfully in practice and PAC analysis of these methods have been developed. But the key notion of relatedness between tasks has not yet been defined clearly, which makes it difficult to understand, let alon...

Transfer learning considers related but distinct tasks defined on heterogenous domains and tries to transfer knowledge between these tasks to improve generalization performance. It is particularly useful when we do not have sufficient amount of labeled training data in some tasks, which may be very costly, laborious, or even infeasible to obtain. Instead, learning the tasks jointly enables us t...

Transfer learning algorithms are used when one has sufficient training data for one supervised learning task (the source task) but only very limited training data for a second task (the target task) that is similar but not identical to the first. These algorithms use varying assumptions about the similarity between the tasks to carry information from the source to the target task. Common assump...

Transfer learning has recently attracted significant research attention, as it simultaneously learns from different source domains, which have plenty of labeled data, and transfers the relevant knowledge to the target domain with limited labeled data to improve the prediction performance. We propose a Bayesian transfer learning framework where the source and target domains are related through t...

We organized a data mining challenge in “unsupervised and transfer learning” (the UTL challenge) followed by a workshop of the same name at the ICML 2011 conference in Bellevue, Washington1. This introduction presents the highlights of the outstanding contributions that were made, which are regrouped in this issue of JMLR W&CP. Novel methodologies emerged to capitalize on large volumes of unlab...

The objective of transfer reinforcement learning is to generalize from a set of previous tasks to unseen new tasks. In this work, we focus on the transfer scenario where the dynamics among tasks are the same, but their goals differ. Although general value function (Sutton et al., 2011) has been shown to be useful for knowledge transfer, learning a universal value function can be challenging in ...

Deep learning models have demonstrated improved efficacy in image classification since the ImageNet Large Scale Visual Recognition Challenge started 2010. Classification of images has further augmented field computer vision with dawn transfer learning. To train a model on huge dataset demands computational resources and add lot cost to Transfer allows reduce also help avoid reinventing wheel. T...

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...

Three pigeons were trained in a three-item simultaneous same/different task. Three of six stimulus combinations were not trained (untrained set) and were tested later. Following acquisition, the subjects were tested with novel stimuli, the untrained set, training-stimulus inversions, and object shape and color manipulations. There was no novel-stimulus transfer--that is, no abstract-concept lea...