Optimizing implementations for object-oriented languages rely on aggressive inlining to achieve good performance. Sometimes the compiler is over-eager in its quest for good performance, however, and inlines too many methods that merely increase compile time and consume extra compiled code space with little benefit in run-time performance. We have designed and implemented a new approach to inlin...

We study unsupervised methods for learning refinements of the nonterminals in a treebank. Following Matsuzaki et al. (2005) and Prescher (2005), we may for example split NP without supervision into NP[0] and NP[1], which behave differently. We first propose to learn a PCFG that adds such features to nonterminals in such a way that they respect patterns of linguistic feature passing: each node’s...

Can we create engaging training programs that improve working memory (WM) skills? While there are numerous procedures that attempt to do so, there is a great deal of controversy regarding their efficacy. Nonetheless, recent meta-analytic evidence shows consistent improvements across studies on lab-based tasks generalizing beyond the specific training effects (Au et al., 2014; Karbach and Verhae...

With the rapid development of Deep Convolutional Neural Networks (DCNNs), numerous works focus on designing better network architectures (i.e., AlexNet, VGG, Inception, ResNet and DenseNet etc.). Nevertheless, all these networks have the same characteristic: each convolutional layer is followed by an activation layer, a Rectified Linear Unit (ReLU) layer is the most used among them. In this wor...