Search Results for author: Haidar Khan

Found 13 papers, 1 papers with code

Limitations of Knowledge Distillation for Zero-shot Transfer Learning

no code implementations EMNLP (sustainlp) 2021 Saleh Soltan, Haidar Khan, Wael Hamza

We demonstrate that in contradiction to the previous observation in the case of monolingual distillation, in multilingual settings, distillation during pretraining is more effective than distillation during fine-tuning for zero-shot transfer learning.

Knowledge Distillation Transfer Learning +1

Output Randomization: A Novel Defense for both White-box and Black-box Adversarial Models

no code implementations8 Jul 2021 Daniel Park, Haidar Khan, Azer Khan, Alex Gittens, Bülent Yener

Adversarial examples pose a threat to deep neural network models in a variety of scenarios, from settings where the adversary has complete knowledge of the model in a "white box" setting and to the opposite in a "black box" setting.

Using multiple ASR hypotheses to boost i18n NLU performance

no code implementations ICON 2020 Charith Peris, Gokmen Oz, Khadige Abboud, Venkata sai Varada, Prashan Wanigasekara, Haidar Khan

For IC and NER multi-task experiments, when evaluating on the mismatched test set, we see improvements across all domains in German and in 17 out of 19 domains in Portuguese (improvements based on change in SeMER scores).

Abstractive Text Summarization Automatic Speech Recognition +5

Optimal Mini-Batch Size Selection for Fast Gradient Descent

no code implementations15 Nov 2019 Michael P. Perrone, Haidar Khan, Changhoan Kim, Anastasios Kyrillidis, Jerry Quinn, Valentina Salapura

This paper presents a methodology for selecting the mini-batch size that minimizes Stochastic Gradient Descent (SGD) learning time for single and multiple learner problems.

Machine Translation Translation

Thwarting finite difference adversarial attacks with output randomization

no code implementations ICLR 2020 Haidar Khan, Daniel Park, Azer Khan, Bülent Yener

Adversarial examples pose a threat to deep neural network models in a variety of scenarios, from settings where the adversary has complete knowledge of the model and to the opposite "black box" setting.

Adversarial Attack

Deep density ratio estimation for change point detection

no code implementations23 May 2019 Haidar Khan, Lara Marcuse, Bülent Yener

In this work, we propose new objective functions to train deep neural network based density ratio estimators and apply it to a change point detection problem.

Change Point Detection Density Ratio Estimation +1

Generation & Evaluation of Adversarial Examples for Malware Obfuscation

no code implementations9 Apr 2019 Daniel Park, Haidar Khan, Bülent Yener

There has been an increased interest in the application of convolutional neural networks for image based malware classification, but the susceptibility of neural networks to adversarial examples allows malicious actors to evade classifiers.

General Classification Malware Classification

Learning filter widths of spectral decompositions with wavelets

1 code implementation NeurIPS 2018 Haidar Khan, Bulent Yener

Our results show that the WD layer can improve neural network based time series classifiers both in accuracy and interpretability by learning directly from the input signal.

Time Series Time Series Classification

Focal onset seizure prediction using convolutional networks

no code implementations29 May 2018 Haidar Khan, Lara Marcuse, Madeline Fields, Kalina Swann, Bülent Yener

Significance: We demonstrate that a robust set of features can be learned from scalp EEG that characterize the preictal state of focal seizures.

EEG Seizure prediction

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