Home /

Research

Showing 385 - 390 / 897

Low-Dimensional Manifolds Support Multiplexed Integrations in Recurrent Neural Networks


Authors:  ArnaudFanthomme, RémiMonasson....
Published date-11/20/2020

Abstract: We study the learning dynamics and the representations emerging in Recurrent Neural Networks trained to integrate one or multiple temporal signals. Combining analytical and numerical investigations, we characterize the conditions …

Learning Informative Representations of Biomedical Relations with Latent Variable Models


Authors:  HarshilShah, JulienFauqueur....
Published date-11/20/2020
Tasks:  LatentVariableModels, RelationExtraction

Abstract: Extracting biomedical relations from large corpora of scientific documents is a challenging natural language processing task. Existing approaches usually focus on identifying a relation either in a single sentence (mention-level) …

Concentration inequality for U-statistics of order two for uniformly ergodic Markov chains, and applications


Authors:  QuentinDuchemin, YohanndeCastro, ClaireLacour....
Published date-11/20/2020

Abstract: We prove a new concentration inequality for U-statistics of order two for uniformly ergodic Markov chains. Working with bounded $\pi$-canonical kernels, we show that we can recover the convergence rate …

Action Duration Prediction for Segment-Level Alignment of Weakly-Labeled Videos


Authors:  RezaGhoddoosian, SaifSayed, VassilisAthitsos....
Published date-11/20/2020

Abstract: This paper focuses on weakly-supervised action alignment, where only the ordered sequence of video-level actions is available for training. We propose a novel Duration Network, which captures a short temporal …

Born Identity Network: Multi-way Counterfactual Map Generation to Explain a Classifier's Decision


Authors:  KwanseokOh, JeeSeokYoon, Heung-IlSuk....
Published date-11/20/2020

Abstract: There exists an apparent negative correlation between performance and interpretability of deep learning models. In an effort to reduce this negative correlation, we propose Born Identity Network (BIN), which is …

Graph Signal Recovery Using Restricted Boltzmann Machines


Authors:  AnkithMohan, AiichiroNakano, EmilioFerrara....
Published date-11/20/2020
Tasks:  Denoising

Abstract: We propose a model-agnostic pipeline to recover graph signals from an expert system by exploiting the content addressable memory property of restricted Boltzmann machine and the representational ability of a …

Filter by

Categories

Tags