Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 5 of 5
Full-Text Articles in Entire DC Network
Wakening Past Concepts Without Past Data: Class-Incremental Learning From Online Placebos, Yaoyao Liu, Yingying Li, Bernt Schiele, Qianru Sun
Wakening Past Concepts Without Past Data: Class-Incremental Learning From Online Placebos, Yaoyao Liu, Yingying Li, Bernt Schiele, Qianru Sun
Research Collection School Of Computing and Information Systems
Not forgetting old class knowledge is a key challenge for class-incremental learning (CIL) when the model continuously adapts to new classes. A common technique to address this is knowledge distillation (KD), which penalizes prediction inconsistencies between old and new models. Such prediction is made with almost new class data, as old class data is extremely scarce due to the strict memory limitation in CIL. In this paper, we take a deep dive into KD losses and find that "using new class data for KD"not only hinders the model adaption (for learning new classes) but also results in low efficiency for …
Solving Online Threat Screening Games Using Constrained Action Space Reinforcement Learning, Sanket Shah, Arunesh Sinha, Pradeep Varakantham, Andrew Perrault, Millind Tambe
Solving Online Threat Screening Games Using Constrained Action Space Reinforcement Learning, Sanket Shah, Arunesh Sinha, Pradeep Varakantham, Andrew Perrault, Millind Tambe
Research Collection School Of Computing and Information Systems
Large-scale screening for potential threats with limited resources and capacity for screening is a problem of interest at airports, seaports, and other ports of entry. Adversaries can observe screening procedures and arrive at a time when there will be gaps in screening due to limited resource capacities. To capture this game between ports and adversaries, this problem has been previously represented as a Stackelberg game, referred to as a Threat Screening Game (TSG). Given the significant complexity associated with solving TSGs and uncertainty in arrivals of customers, existing work has assumed that screenees arrive and are allocated security resources at …
Optimal Adaptation In Web Processes With Coordination Constraints, Kunal Verma, Prashant Doshi, Karthik Gomadam, John A. Miller, Amit P. Sheth
Optimal Adaptation In Web Processes With Coordination Constraints, Kunal Verma, Prashant Doshi, Karthik Gomadam, John A. Miller, Amit P. Sheth
Kno.e.sis Publications
We present methods for optimally adapting Web processes to exogenous events while preserving inter-service constraints that necessitate coordination. For example, in a supply chain process, orders placed by a manufacturer may get delayed in arriving. In response to this event, the manufacturer has the choice of either waiting out the delay or changing the supplier. Additionally, there may be compatibility constraints between the different orders, thereby introducing the problem of coordination between them if the manufacturer chooses to change the suppliers. We focus on formulating the decision making models of the managers, who must adapt to external events while satisfying …
Optimal Adaptation In Autonomic Web Processes With Inter-Service Dependencies, Kunal Verma, Prashant Doshi, Karthik Gomadam, John A. Miller, Amit P. Sheth
Optimal Adaptation In Autonomic Web Processes With Inter-Service Dependencies, Kunal Verma, Prashant Doshi, Karthik Gomadam, John A. Miller, Amit P. Sheth
Kno.e.sis Publications
We present methods for optimally adapting Web processes to exogenous events while preserving inter-service dependencies. For example, in a supply chain process, orders placed by the manufacturer may get delayed in arriving. In response to this event, the manufacturer has the choice of either waiting out the delay or changing the supplier.
Prioritization Methods For Accelerating Mdp Solvers, Kevin Seppi, David Wingate
Prioritization Methods For Accelerating Mdp Solvers, Kevin Seppi, David Wingate
Faculty Publications
The performance of value and policy iteration can be dramatically improved by eliminating redundant or useless backups, and by backing up states in the right order. We study several methods designed to accelerate these iterative solvers, including prioritization, partitioning, and variable reordering. We generate a family of algorithms by combining several of the methods discussed, and present extensive empirical evidence demonstrating that performance can improve by several orders of magnitude for many problems, while preserving accuracy and convergence guarantees.