no code implementations • 30 Jan 2024 • Thomas Degris, Khurram Javed, Arsalan SharifNassab, Yuxin Liu, Richard Sutton
We conclude by suggesting that combining both approaches could be a promising future direction to improve the performance of neural networks in continual learning.
no code implementations • 10 Jul 2023 • Vincent Liu, Han Wang, Ruo Yu Tao, Khurram Javed, Adam White, Martha White
Lastly, we outline a class of algorithms which we call online-aware that are designed to mitigate interference, and show they do reduce interference according to our measure and that they improve stability and performance in several classic control environments.
1 code implementation • 20 Jan 2023 • Khurram Javed, Haseeb Shah, Rich Sutton, Martha White
We show that by either decomposing the network into independent modules or learning the network in stages, we can make RTRL scale linearly with the number of parameters.
no code implementations • 23 Feb 2022 • Cameron Haigh, Zichen Zhang, Negar Hassanpour, Khurram Javed, Yingying Fu, Shayan Shahramian, Shawn Zhang, Jun Luo
In light of the need to tweak the target specifications throughout the circuit design cycle, we also develop a variant in which the agent can learn to quickly adapt to draw new inductors for moderately different target specifications.
1 code implementation • 9 Mar 2021 • Khurram Javed, Martha White, Rich Sutton
We empirically show that as long as connections between columns are sparse, our method approximates the true gradient well.
1 code implementation • 12 Jun 2020 • Khurram Javed, Martha White, Yoshua Bengio
One solution for achieving strong generalization is to incorporate causal structures in the models; such structures constrain learning by ignoring correlations that contradict them.
no code implementations • 3 Oct 2019 • Khurram Javed, Hengshuai Yao, Martha White
Gradient-based meta-learning has proven to be highly effective at learning model initializations, representations, and update rules that allow fast adaptation from a few samples.
1 code implementation • 25 Jun 2019 • Samuel Sokota, Ryan D'Orazio, Khurram Javed, Humza Haider, Russell Greiner
In this paper, we demonstrate that an existing method for estimating simultaneous prediction intervals from samples can easily be adapted for patient-specific survival curve analysis and yields accurate results.
6 code implementations • NeurIPS 2019 • Khurram Javed, Martha White
We show that it is possible to learn naturally sparse representations that are more effective for online updating.
2 code implementations • 8 Jul 2018 • Khurram Javed, Faisal Shafait
To this end, we first thoroughly analyze the current state of the art (iCaRL) method for incremental learning and demonstrate that the good performance of the system is not because of the reasons presented in the existing literature.
1 code implementation • 8 Jul 2018 • Haseeb Shah, Khurram Javed, Faisal Shafait
We discuss the biases in current Generative Adversarial Networks (GAN) based approaches that learn the classifier by knowledge distillation from previously trained classifiers.
1 code implementation • ICDAR2017 2017 • Khurram Javed, Faisal Shafait
We propose a document segmentation algorithm that recursively uses convolutional neural networks to precisely localize a document in a natural image.