Concept bottleneck models (CBMs) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then final label based on concept predictions. We extend CBMs interactive settings where model can query a human collaborator some concepts. develop an interaction policy that, at time, chooses which request so as maximally improve pr...

Knowledge acquisition is a serious bottleneck for natural language understanding systems. For this reason, large-scale linguistic resources have been compiled and made available by organizations such as the Linguistic Data Consortium (Comlex) and Princeton University (WordNet). Systems making use of these resources can greatly accelerate the development process by avoiding the need for the deve...

Performance of data streaming applications is codetermined by both networking and computing resources, which should be allocated in an integrated and cooperative way. Dynamic controlling of resource allocation is required since unilateral redundancy in networking or computing resources may result in underutilization but not necessarily high performance since insufficiency of either resource may...

Web 2.0 applications as social networking websites deal with a dynamic and various transaction workload. A middleware approach can be considered as a suitable solution for facing those various workloads. However, even if the middleware resources may be distributed for scalability and availability, they can be a bottleneck or underused when the workload varies permanently. We propose a solution ...

In this paper we investigate the stationary profiles of a nonlinear Fokker-Planck equation with small diffusion and in- outflow boundary conditions. We consider corridors bottleneck whose width has global nondegenerate minimum in interior. limit are obtained constructively by using methods from geometric singular perturbation theory (GSPT). identify three main types corresponding to: (i) high d...

By harnessing available computing resources on the network, computational grids can deliver large amounts of computing capacity to the high energy physics (HEP) community. Supporting HEP applications, which typically make heavy memory and I/O demands, requires careful co-allocation of network, storage, and computing resources. The grid manager must ensure that applications have the necessary re...

Modern computer systems make use of multiple cores and NUMA (Non Uniform Memory Access) architecture. Since multiple cores share various microarchitectural resources such as LLC (Last Level Cache), memory interface and interconnect, contentions on these resources become a serious performance bottleneck. In this paper, we explore research issues how to manage these resources to mitigate such con...

Repetitious access to remote resources, usually data, constitutes a bottleneck for many software systems. Caching is a technique that can drastically improve the performance of any database application, by avoiding multiple read operations for the same data. This paper addresses the caching problems from a pattern perspective. Both Caching and caching strategies, like primed and on demand, are ...