Amirata Ghorbani, PhD
Palo Alto, California, United States
6K followers
500+ connections
About
https://www.amiratag.com/
I received my Ph.D. in Machine Learning from the…
Experience
Education
-
Stanford University
-
Activities and Societies: Stanford Graduate Fellowship (SGF) Robert Bosch Fellow (the most prestigious Stanford fellowship awarded to graduate students.)
-
-
-
-
Activities and Societies: Iran's National Elite Foundation Scholarship
-Ranked 2nd, Class of 2012-2016
-
-
Licenses & Certifications
Publications
-
How Does Mixup Help With Robustness and Generalization?
International Conference on Learning Representations (ICLR)
-
Improving Adversarial Robustness via Unlabeled Out-of-Domain Data
International Conference on Artificial Intelligence and Statistics
-
A Distributional Framework for Data Valuation
Proceedings of the 37th International Conference on Machine Learning, PMLR
-
Neuron Shapley: Discovering the Responsible Neurons
Advances in Neural Information Processing Systems 33 (NeurIPS 2020)
-
Interpretation of neural networks is fragile
The Thirty-Third AAAI Conference on Artificial Intelligence
-
Data Shapley: Equitable Valuation of Data for Machine Learning
36th International Conference on Machine Learning
-
Knockoffs for the mass: new feature importance statistics with false discovery guarantees
The 22nd International Conference on Artificial Intelligence and Statistics
-
Multiaccuracy: Black-box post-processing for fairness in classification
Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society
-
Towards Automatic Concept-based Explanations
Advances in Neural Information Processing Systems 32 (NeurIPS 2019)
-
Embedding for Informative Missingness: Deep Learning With Incomplete Data
56th Annual Allerton Conference on Communication, Control, and Computing
-
Blind iterative non-linear distortion compensation based on thresholding
IEEE transactions on circuits & systems II
The sampling process in electrical devices includes non-linear distortion which needs to be compensated to boost up the system efficiency. In this paper, a blind method is suggested for non-linear distortion compensation. The core idea is to leverage the sparsity of the signal to cope with the ill-posedness of the distortion compensation task.
Other authorsSee publication
Courses
-
Analysis of Deep Learning
STATS 385
-
Biomedical Image Analysis and Interpretation
BIOMEDIN260
-
Convex Optimization
EE 364a
-
Convolutional Neural Networks for Visual Recognition
CS 231n
-
Data Mining
STATS 315B
-
Deep Learning in Genomics and Biomedicine
CS 273b
-
Digital Image Processing
-
-
Linear Dynamical Systems
EE 263
-
Machine Learning
CS 229
-
Natural Language Processing with Deep Learning
CS 224N
-
Probabilistic Graphical Models
CS228
-
Reinforcement Learning
MS&E 338
-
Statistical Signal Processing
EE 278
-
Theory Of Statistics I
STATS300A
-
Wireless Communications
-
Honors & Awards
-
3rd Rank, Stanford EE PhD Qualifying Exam (among more than 80 PhD students)
-
-
Stanford Graduate Fellowship in Science & Engineering (Robert Bosch Fellow)
-
Only offered to the most outstanding students pursuing doctoral degrees in science and engineering.
-
Ranked 2nd in Sharif University Electrical Engineering Undergraduate Class of 2016
-
-
Member of Iran's National Elite Foundation
-
-
Ranked 9th in Iran's Nationwide University Entrance Exam
-
Test Scores
-
Graduate Record Examinations (GRE)
Score: 325
-
Test of English as a Foreign Language (TOEFL)
Score: 112
Languages
-
English
Full professional proficiency
-
Azerbaijani
Native or bilingual proficiency
-
Persian
Native or bilingual proficiency
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More