With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
Multi-core processors with ever increasing number of cores per chip are becoming prevalent in modern parallel computing. Our goal is to make use of the multi-core as well as multi...
Lei Li, Wenjie Fu, Fan Guo, Todd C. Mowry, Christo...
This paper considers the regularized learning algorithm associated with the leastsquare loss and reproducing kernel Hilbert spaces. The target is the error analysis for the regres...
Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework i...
Abstract—This paper presents a novel study on how to distribute neural networks in a wireless sensor networks (WSNs) such that the energy consumption is minimized while improving...