Search Results for author: Aya Abdelsalam Ismail

Found 6 papers, 3 papers with code

Interpretable Mixture of Experts

no code implementations5 Jun 2022 Aya Abdelsalam Ismail, Sercan Ö. Arik, Jinsung Yoon, Ankur Taly, Soheil Feizi, Tomas Pfister

In addition to constituting a standalone inherently-interpretable architecture, IME has the premise of being integrated with existing DNNs to offer interpretability to a subset of samples while maintaining the accuracy of the DNNs.

Decision Making Time Series

Improving Deep Learning Interpretability by Saliency Guided Training

1 code implementation NeurIPS 2021 Aya Abdelsalam Ismail, Héctor Corrada Bravo, Soheil Feizi

In this paper, we tackle this issue and introduce a {\it saliency guided training}procedure for neural networks to reduce noisy gradients used in predictions while retaining the predictive performance of the model.

Time Series Time Series Analysis

Improving Multimodal Accuracy Through Modality Pre-training and Attention

no code implementations11 Nov 2020 Aya Abdelsalam Ismail, Mahmudul Hasan, Faisal Ishtiaq

Training a multimodal network is challenging and it requires complex architectures to achieve reasonable performance.

Emotion Recognition Sentiment Analysis

Improving Long-Horizon Forecasts with Expectation-Biased LSTM Networks

no code implementations18 Apr 2018 Aya Abdelsalam Ismail, Timothy Wood, Héctor Corrada Bravo

State-of-the-art forecasting methods using Recurrent Neural Net- works (RNN) based on Long-Short Term Memory (LSTM) cells have shown exceptional performance targeting short-horizon forecasts, e. g given a set of predictor features, forecast a target value for the next few time steps in the future.

Management

Cannot find the paper you are looking for? You can Submit a new open access paper.