EC-KitY is a comprehensive Python library for doing evolutionary computation (EC), licensed under the BSD 3-Clause License, and compatible with scikit-learn. Designed with modern softwareengineering and machine learn...
详细信息
作者:
Johnson, Taylor T.Vanderbilt University
Department of Electrical Engineering and Computer Science Institute for Software Integrated Systems NashvilleTN United States
This report presents the results of the repeatability evaluation for the 4th International Competition on Verifying Continuous and Hybrid systems (ARCH-COMP’20). The competition took place as part of the workshop App...
详细信息
The development and implementation of the latest information technologies for contact tracking in the context of the COVID-19 pandemic is an extremely important and urgent task, which is directly related to the possib...
详细信息
The pleasure that often comes with eating can be further enhanced with intelligent technology, as the field of human-food interaction suggests. However, knowledge on how to design such pleasure-supporting eating syste...
详细信息
Deep reinforcement learning has proven remarkably useful in training agents from unstructured data. However, the opacity of the produced agents makes it difficult to ensure that they adhere to various requirements pos...
详细信息
Spread-Spectrum Steganography (SSS) technology is used to hide information messages in image containers. For this purpose, propagating discrete signals are used, in specially formed pseudo-random sequences (PRS) with ...
详细信息
Human-computer interaction (HCI) is an evolving field of research that focuses on understanding and improving the communication and interaction between humans and computers. Over the past decades, we have seen many si...
Human-computer interaction (HCI) is an evolving field of research that focuses on understanding and improving the communication and interaction between humans and computers. Over the past decades, we have seen many significant advances in this field, which have contributed to the widespread adoption and integration of technology into our daily lives. HCI research and development aims to design information technology systems to meet the needs and preferences of users. Usability, efficiency, accessibility and user satisfaction are important considerations in HCI design. This paper presents the results of a pilot study on user acceptance of HCIs. The results show that users are positive about and willing to use HCIs.
Diabetes complications have a significant impact on patients’ quality of life. The objective of this study was to predict which patients were more likely to be in a complicated health condition at the time of admissi...
详细信息
Recent advances in single image super-resolution (SISR) have achieved remarkable performance through deep learning. However, the high computational cost hinders the deployment of SISR models on edge devices. Instead o...
Recent advances in single image super-resolution (SISR) have achieved remarkable performance through deep learning. However, the high computational cost hinders the deployment of SISR models on edge devices. Instead of proposing new SISR models, a new trend is emerging to improve network efficiency by reducing parameters, FLOPs, and inference time through slight modifications to the original models. However, recent methods usually focus on reducing only one of three metrics, i.e., FLOPs, parameters and inference time, which inevitably increases the other two metrics. In this paper, we propose a novel Adaptive Student Inference Network (ASIN) on popular SISR models, which aims at reducing FLOPs and inference time while maintaining the number of parameters and restoring clearer high-resolution images. Specifically, our ASIN divides a SISR model into three components (head, body and tail) and adopts various strategies for each part. For head and tail parts, to ensure the restored images contain more detailed information, a novel auxiliary Enhanced Teacher Network (ETNet) is designed, which is trained with the ground-truth images to obtain more prior knowledge to guide student network to extract more accurate textures using a new knowledge distillation method. For the body part, owing to the varying difficulties of the reconstructions in different regions, we propose an Adaptive Depth Predicted Module (ADPM) to dynamically shorten average depth of network to reduce the computational cost of overall network. Extensive experiments on two datasets demonstrate the effectiveness and state-of-the-art performance of our ASIN compared to its counterparts.
Edge AI-based reinforcement learning is less reliant on mathematical models and relies on experience to help with the design and optimization of Consumer Technology models, making it ideal for learning dynamic treatme...
详细信息
暂无评论