Hierarchical phrase-based models provide a powerful mechanism to capture non-local phrase reorderings for statistical machine translation (SMT). However, many phrase reorderings a...
In this paper, we use linear approximations of the addition modulo 2n of three n-bit integers to identify linear approximations of g1, g2, the feedback functions of HC-128. This, i...
Log-linear models have recently been used in acoustic modeling for speech recognition systems. This has been motivated by competitive results compared to systems based on Gaussian...
Protein function prediction is an active area of research in bioinformatics. And yet, transfer of annotation on the basis of sequence or structural similarity remains widely used ...
In this paper, we propose a novel adaptive step-size approach for policy gradient reinforcement learning. A new metric is defined for policy gradients that measures the effect of ...
Takamitsu Matsubara, Tetsuro Morimura, Jun Morimot...