Task (computing)

About: Task (computing) is a research topic. Over the lifetime, 9718 publications have been published within this topic receiving 129364 citations.

Exploiting Unrelated Tasks in Multi-Task Learning

Abstract: We study the problem of learning a group of principal tasks using a group of auxiliary tasks, unrelated to the principal ones. In many applications, joint learning of unrelated tasks which use the same input data can be beneficial. The reason is that prior knowledge about which tasks are unrelated can lead to sparser and more informative representations for each task, essentially screening out idiosyncrasies of the data distribution. We propose a novel method which builds on a prior multitask methodology by favoring a shared low dimensional representation within each group of tasks. In addition, we impose a penalty on tasks from different groups which encourages the two representations to be orthogonal. We further discuss a condition which ensures convexity of the optimization problem and argue that it can be solved by alternating minimization. We present experiments on synthetic and real data, which indicate that incorporating unrelated tasks can improve significantly over standard multi-task learning methods.

Method and system for prioritizing tasks made available by devices in a network

Abstract: A method and system that facilitates prioritization of tasks available through the devices in a home network. The tasks are user level descriptions of the high-level actions a user and underlying devices can perform. By prioritizing tasks for a user, the present invention aims to minimize the effort required to compare and comprehend the usefulness and feasibility of tasks. In doing so, the number of tasks possible to a user can be reduced and the highest priority task for a given user and device can be used by the application software as the suggested ‘most likely’ task for the user.

RGEM: A Responsive GPGPU Execution Model for Runtime Engines

Abstract: General-purpose computing on graphics processing units, also known as GPGPU, is a burgeoning technique to enhance the computation of parallel programs. Applying this technique to real-time applications, however, requires additional support for timeliness of execution. In particular, the non-preemptive nature of GPGPU, associated with copying data to/from the device memory and launching code onto the device, needs to be managed in a timely manner. In this paper, we present a responsive GPGPU execution model (RGEM), which is a user-space runtime solution to protect the response times of high-priority GPGPU tasks from competing workload. RGEM splits a memory-copy transaction into multiple chunks so that preemption points appear at chunk boundaries. It also ensures that only the highest-priority GPGPU task launches code onto the device at any given time, to avoid performance interference caused by concurrent launches. A prototype implementation of an RGEM-based CUDA runtime engine is provided to evaluate the real-world impact of RGEM. Our experiments demonstrate that the response times of high-priority GPGPU tasks can be protected under RGEM, whereas their response times increase in an unbounded fashion without RGEM support, as the data sizes of competing workload increase.

Distributed computing of a job corresponding to a plurality of predefined tasks

Abstract: In a distributed computing environment, a queue of jobs is maintained on a job database, along with parameters for each of the computing devices available to process the jobs. A task model defining the job is provided for generating a plurality of tasks comprising each job. The tasks are maintained in a tuple database, along with the status of each task, indicating when each task is ready for processing. As a computing device becomes available to process a task, its capabilities are matched with those required to complete tasks that are ready for processing and the highest priority task meeting those requirements is assigned to the computing device to be processed. These steps are repeated until all the tasks required for the job have been processed, or the job is otherwise terminated.

RLBench: The Robot Learning Benchmark & Learning Environment

Abstract: We present a challenging new benchmark and learning-environment for robot learning: RLBench. The benchmark features 100 completely unique, hand-designed tasks, ranging in difficulty from simple target reaching and door opening to longer multi-stage tasks, such as opening an oven and placing a tray in it. We provide an array of both proprioceptive observations and visual observations, which include rgb, depth, and segmentation masks from an over-the-shoulder stereo camera and an eye-in-hand monocular camera. Uniquely, each task comes with an infinite supply of demos through the use of motion planners operating on a series of waypoints given during task creation time; enabling an exciting flurry of demonstration-based learning possibilities. RLBench has been designed with scalability in mind; new tasks, along with their motion-planned demos, can be easily created and then verified by a series of tools, allowing users to submit their own tasks to the RLBench task repository. This large-scale benchmark aims to accelerate progress in a number of vision-guided manipulation research areas, including: reinforcement learning, imitation learning, multi-task learning, geometric computer vision, and in particular, few-shot learning. With the benchmark's breadth of tasks and demonstrations, we propose the first large-scale few-shot challenge in robotics. We hope that the scale and diversity of RLBench offers unparalleled research opportunities in the robot learning community and beyond. Benchmarking code and videos can be found at https://sites.google.com/view/rlbench .