Search Results for author: Khurram Javed

Found 12 papers, 8 papers with code

Step-size Optimization for Continual Learning

no code implementations30 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.

Continual Learning

Measuring and Mitigating Interference in Reinforcement Learning

no code implementations10 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.

reinforcement-learning

Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks

1 code implementation20 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.

Atari Games

Drawing Inductor Layout with a Reinforcement Learning Agent: Method and Application for VCO Inductors

no code implementations23 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.

Reinforcement Learning (RL)

Scalable Online Recurrent Learning Using Columnar Neural Networks

1 code implementation9 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.

Meta-Learning

Learning Causal Models Online

1 code implementation12 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.

Continual Learning

Is Fast Adaptation All You Need?

no code implementations3 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.

Incremental Learning Meta-Learning

Simultaneous Prediction Intervals for Patient-Specific Survival Curves

1 code implementation25 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.

Descriptive Prediction Intervals +2

Meta-Learning Representations for Continual Learning

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.

Continual Learning Meta-Learning

Revisiting Distillation and Incremental Classifier Learning

2 code implementations8 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.

Incremental Learning Knowledge Distillation

Distillation Techniques for Pseudo-rehearsal Based Incremental Learning

1 code implementation8 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.

Incremental Learning Knowledge Distillation

Real-time Document Localization in Natural Images by Recursive Application of a CNN.

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.

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