Home /
Research
Showing 691 - 696 / 904
CapWAP: Captioning with a Purpose
AdamFisch, KentonLee, Ming-WeiChang....
Published date-11/09/2020
ImageCaptioning, QuestionAnswering, VisualQuestionAnswering
The traditional image captioning task uses generic reference captions to provide textual information about images. Different user populations, however, will care about different visual aspects of images. In this paper, …
Particles to Partial Differential Equations Parsimoniously
HassanArbabi, IoannisKevrekidis....
Published date-11/09/2020
Equations governing physico-chemical processes are usually known at microscopic spatial scales, yet one suspects that there exist equations, e.g. in the form of Partial Differential Equations (PDEs), that can explain …
Adaptive Learning of Rank-One Models for Efficient Pairwise Sequence Alignment
GovindaM.Kamath, TavorZ.Baharav, IlanShomorony....
Published date-11/09/2020
Pairwise alignment of DNA sequencing data is a ubiquitous task in bioinformatics and typically represents a heavy computational burden. State-of-the-art approaches to speed up this task use hashing to identify …
Improving Neural Network Training in Low Dimensional Random Bases
FrithjofGressmann, ZachEaton-Rosen, CarloLuschi....
Published date-11/09/2020
Stochastic Gradient Descent (SGD) has proven to be remarkably effective in optimizing deep neural networks that employ ever-larger numbers of parameters. Yet, improving the efficiency of large-scale optimization remains a …
Numerical Exploration of Training Loss Level-Sets in Deep Neural Networks
NaveedTahir, GarrettE.Katz....
Published date-11/09/2020
DimensionalityReduction
We present a computational method for empirically characterizing the training loss level-sets of deep neural networks. Our method numerically constructs a path in parameter space that is constrained to a …
Explaining Deep Graph Networks with Molecular Counterfactuals
DaniloNumeroso, DavideBacciu....
Published date-11/09/2020
We present a novel approach to tackle explainability of deep graph networks in the context of molecule property prediction tasks, named MEG (Molecular Explanation Generator). We generate informative counterfactual explanations …