1 code implementation • 19 Apr 2023 • Shoaib Ahmed Siddiqui, David Krueger, Thomas Breuel
Modern deep learning architectures for object recognition generalize well to novel views, but the mechanisms are not well understood.
1 code implementation • 3 Feb 2023 • Shoaib Ahmed Siddiqui, David Krueger, Yann Lecun, Stéphane Deny
Current state-of-the-art deep networks are all powered by backpropagation.
no code implementations • 27 Nov 2022 • Alan Clark, Shoaib Ahmed Siddiqui, Robert Kirk, Usman Anwar, Stephen Chung, David Krueger
Existing offline reinforcement learning (RL) algorithms typically assume that training data is either: 1) generated by a known policy, or 2) of entirely unknown origin.
1 code implementation • 20 Sep 2022 • Shoaib Ahmed Siddiqui, Nitarshan Rajkumar, Tegan Maharaj, David Krueger, Sara Hooker
Modern machine learning research relies on relatively few carefully curated datasets.
1 code implementation • 13 Jun 2022 • Adriano Lucieri, Fabian Schmeisser, Christoph Peter Balada, Shoaib Ahmed Siddiqui, Andreas Dengel, Sheraz Ahmed
Interestingly, despite deep feature extractors being inclined towards learning entangled features for skin lesion classification, individual features can still be decoded from this entangled representation.
no code implementations • 3 Mar 2022 • Pervaiz Iqbal Khan, Shoaib Ahmed Siddiqui, Imran Razzak, Andreas Dengel, Sheraz Ahmed
The idea is to learn word representation by its surrounding words and utilize emojis in the text to help improve the classification results.
no code implementations • 10 Jul 2021 • Shoaib Ahmed Siddiqui, Thomas Breuel
In this paper, we investigate the use of pretraining with adversarial networks, with the objective of discovering the relationship between network depth and robustness.
1 code implementation • 3 Dec 2020 • Vinu Joseph, Shoaib Ahmed Siddiqui, Aditya Bhaskara, Ganesh Gopalakrishnan, Saurav Muralidharan, Michael Garland, Sheraz Ahmed, Andreas Dengel
With the rise in edge-computing devices, there has been an increasing demand to deploy energy and resource-efficient models.
no code implementations • 30 Aug 2020 • Shoaib Ahmed Siddiqui, Andreas Dengel, Sheraz Ahmed
This paves the way for future research in the direction of adversarial attacks and defenses, particularly for time-series data.
no code implementations • 28 May 2020 • Muhammad Naseer Bajwa, Muhammad Imran Malik, Shoaib Ahmed Siddiqui, Andreas Dengel, Faisal Shafait, Wolfgang Neumeier, Sheraz Ahmed
For glaucoma classification we achieved AUC equal to 0. 874 which is 2. 7% relative improvement over the state-of-the-art results previously obtained for classification on ORIGA.
1 code implementation • 5 May 2020 • Dominique Mercier, Shoaib Ahmed Siddiqui, Andreas Dengel, Sheraz Ahmed
Identification of input data points relevant for the classifier (i. e. serve as the support vector) has recently spurred the interest of researchers for both interpretability as well as dataset debugging.
no code implementations • ICLR 2020 • Shoaib Ahmed Siddiqui, Dominique Mercier, Andreas Dengel, Sheraz Ahmed
We approach the problem of interpretability in a novel way by proposing TSInsight where we attach an auto-encoder to the classifier with a sparsity-inducing norm on its output and fine-tune it based on the gradients from the classifier and a reconstruction penalty.
no code implementations • 15 May 2019 • Mohsin Munir, Shoaib Ahmed Siddiqui, Ferdinand Küsters, Dominique Mercier, Andreas Dengel, Sheraz Ahmed
This indicates a vital gap between the explainability provided by the systems and the novice user.
no code implementations • 15 Feb 2019 • Muhammad Ali Chattha, Shoaib Ahmed Siddiqui, Muhammad Imran Malik, Ludger van Elst, Andreas Dengel, Sheraz Ahmed
The promise of ANNs to automatically discover and extract useful features/patterns from data without dwelling on domain expertise although seems highly promising but comes at the cost of high reliance on large amount of accurately labeled data, which is often hard to acquire and formulate especially in time-series domains like anomaly detection, natural disaster management, predictive maintenance and healthcare.
3 code implementations • 19 Dec 2018 • Mohsin Munir, Shoaib Ahmed Siddiqui, Andreas Dengel, Sheraz Ahmed
In contrast to the anomaly detection methods where anomalies are learned, DeepAnT uses unlabeled data to capture and learn the data distribution that is used to forecast the normal behavior of a time series.
1 code implementation • ICML 2018 • Lukas Ruff, Robert Vandermeulen, Nico Goernitz, Lucas Deecke, Shoaib Ahmed Siddiqui, Alexander Binder, Emmanuel Müller, Marius Kloft
Despite the great advances made by deep learning in many machine learning problems, there is a relative dearth of deep learning approaches for anomaly detection.
Ranked #32 on Anomaly Detection on One-class CIFAR-10
1 code implementation • 8 Feb 2018 • Shoaib Ahmed Siddiqui, Dominik Mercier, Mohsin Munir, Andreas Dengel, Sheraz Ahmed
This is a step towards making informed/explainable decisions in the domain of time-series, powered by deep learning.