Transferring Instances for Model-Based Reinforcement Learning. Matthew E. Taylor, Nicholas K. Jong, and Peter Stone. In Machine Learning and Knowledge Discovery in Databases, pp. 488–505, September ...

Citizens and urban planners unite in "Urban Strategy in the Present Tense," a year-long speaker series dedicated to the local roots of civic innovation. From alleyway and open streets to families at ...

The risk that the USE tool that supports UML and OCL might fade away prompts me to reflect on what it does well that Eclipse UML/OCL/Papyrus do not. I am not aware of ...

Unlike the current generation, which comes with split taillights, the Model 3 Highland has the taillights integrated into the trunk lid. This poses issues when the trunk is open, so Tesla had to find ...

Abstract: Domain generalization person re-identification (DG-ReID) aims to train a generalizable model over several source domains that can perform well on unseen target domains, which makes the ...

Abstract: Python has become a standard scientific computing language with fast-growing support of machine learning and data analysis modules, as well as an increasing usage of big data. The Dynamic ...

Dynamic Training (DT) is an experimental fork of MXNet that you can use for dynamically scaling your training jobs. To use the dynamic training feature you start with one or more instances to train a ...