Byoung-Tak Zhang

TL;DR: DGCR8 may function as the molecular anchor that measures the distance from the dsRNA-ssRNA junction and facilitate the prediction of novel microRNAs and will assist in the rational design of small hairpin RNAs for RNA interference.

TL;DR: BAN is proposed that find bilinear attention distributions to utilize given vision-language information seamlessly and quantitatively and qualitatively evaluates the model on visual question answering and Flickr30k Entities datasets, showing that BAN significantly outperforms previous methods and achieves new state-of-the-arts on both datasets.

TL;DR: IMM incrementally matches the moment of the posterior distribution of the neural network which is trained on the first and the second task, respectively to make the search space of posterior parameter smooth.

TL;DR: This article proposed bilinear attention networks (BAN) that find bilinearly attention distributions to utilize given vision-language information seamlessly. But, the computational cost to learn attention distributions for every pair of multimodal input channels is prohibitively expensive.

TL;DR: The essence of the parsimony problem is demonstrated empirically by analyzing error landscapes of programs evolved for neural network synthesis and an adaptive learning method is presented that automatically balances the model-complexity factor to evolve parsimonious programs without losing the diversity of the population needed for achieving the desired training accuracy.