Aya Abdelsalam Ismail

Aya Abdelsalam Ismail 

I am on the job market!

I am a Ph.D. candidate at the University of Maryland, advised by Soheil Feizi and Héctor Corrada Bravo. My research focuses on the interpretability of neural models, long-term forecasting in time series, and applications of deep learning in neuroscience and health informatics.

Email: asalam@cs.umd.edu


Talks and Lectures



Improving Deep Learning Interpretability by Saliency Guided Training

Aya Abdelsalam Ismail, Héctor Corrada Bravo, Soheil Feizi.

NeurIPs 2021.


Benchmarking Deep Learning Interpretability in Time Series Predictions

Aya Abdelsalam Ismail, Mohamed Gunady, Héctor Corrada Bravo, Soheil Feizi.

NeurIPs 2020.


Input-Cell-Attention Reduces Vanishing Saliency of Recurrent Neural Networks

Aya Abdelsalam Ismail, Mohamed Gunady, Luiz Pessoa, Héctor Corrada Bravo, Soheil Feizi.

NeurIPs 2019.


The Alzheimer’s Disease Prediction Of Longitudinal Evolution (TADPOLE) Challenge: Results after 1 Year Follow-up

Razvan V. Marinescu, … et al, Aya Ismail.


Improving Long-Horizon Forecasts with Expectation-Biased LSTM Networks

Aya Abdelsalam Ismail, Timothy Wood, Héctor Corrada Bravo.


LIMO: Learning Programming using Interactive Map Activities

Ruby Y. Tahboub, Jaewoo Shin, Aya Abdelsalam, Jalaleldeen W Aref, Walid G. Aref, Sunil Kumar Prabhakar.



On Map-Centric Programming Environments

Walid G Aref, Sunil Prabhakar, Jaewoo Shin, Ruby Y Tahboub, Aya Abdelsalam, Jalaleldeen W Aref.