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. |
News
I recieved Wylie Dissertation Fellowship.
I will be giving a talk at NCI about Deep learning interpretability.
One paper accepted at NeurIPS 2021.
Talks and Lectures
RNNs, LSTMs and Transformers. (Deep Learning Foundations course)
Deep Learning Interpretations. (Deep Learning Foundations course)
Research
 |
Improving Deep Learning Interpretability by Saliency Guided TrainingAya Abdelsalam Ismail, Héctor Corrada Bravo, Soheil Feizi. NeurIPs 2021. |
 |
Benchmarking Deep Learning Interpretability in Time Series PredictionsAya Abdelsalam Ismail, Mohamed Gunady, Héctor Corrada Bravo, Soheil Feizi. NeurIPs 2020. |
 |
Input-Cell-Attention Reduces Vanishing Saliency of Recurrent Neural NetworksAya 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-upRazvan V. Marinescu, … et al, Aya Ismail. |
 |
Improving Long-Horizon Forecasts with Expectation-Biased LSTM NetworksAya Abdelsalam Ismail, Timothy Wood, Héctor Corrada Bravo. |
 |
LIMO: Learning Programming using Interactive Map ActivitiesRuby Y. Tahboub, Jaewoo Shin, Aya Abdelsalam, Jalaleldeen W Aref, Walid G. Aref, Sunil Kumar Prabhakar. SIGSPATIAL 2015. |
 |
On Map-Centric Programming EnvironmentsWalid G Aref, Sunil Prabhakar, Jaewoo Shin, Ruby Y Tahboub, Aya Abdelsalam, Jalaleldeen W Aref. SIGSPATIAL 2015. |