Multimedia instruction set extensions have become a prominent feature in desktop microprocessor platforms, promising superior performance on a wide range of floating-point and int...
Increased platform heterogeneity and varying resource availability in distributed systems motivates the design of resource-aware applications, which ensure a desired performance l...
We propose a fast batch learning method for linearchain Conditional Random Fields (CRFs) based on Newton-CG methods. Newton-CG methods are a variant of Newton method for high-dime...
Yuta Tsuboi, Yuya Unno, Hisashi Kashima, Naoaki Ok...
Scientific, symbolic, and multimedia applications present diverse computing workloads with different types of inherent parallelism. Tomorrow’s processors will employ varying com...
Linda M. Wills, Tarek M. Taha, Lewis B. Baumstark ...
Recent algorithmic and theoretical advances in reinforcement learning (RL) have attracted widespread interest. RL algorithmshave appeared that approximatedynamic programming on an ...