Attributed to the widespread use of general artificial intelligence (AI), large-scale datasets have become a critical component for the success of AI-powered applications. While collecting a larger dataset is desirabl...
详细信息
the paper investigates various deep learning approaches for classifying movies by genre. To prepare the initial dataset, a system for parsing textual information and images from the Internet Movie Database, IMDB (http...
详细信息
Withthe arrival of big data era and the rapid development of artificial intelligence, deep learning has made breakthroughs in many fields. However, although it has been widely used in many fields, there are still man...
详细信息
Work stealing is a well-known technique for dynamic load balancing;however, manually writing work-stealing protocols is errorprone. We can use the Tascell parallel programming language for the correct and portable imp...
详细信息
ISBN:
(纸本)9798400708893
Work stealing is a well-known technique for dynamic load balancing;however, manually writing work-stealing protocols is errorprone. We can use the Tascell parallel programming language for the correct and portable implementation of work stealing;the implementation combines polling and adequate mutual exclusion. In Tascell, we can express on-demand concurrency for backtracking-based load balancing where a worker performs a sequential computation with its own execution stack unless it is requested to spawn a task. To spawn a larger task by temporarily backtracking, nested functions can be used for legitimate execution stack access. As nested functions for extended C languages, we can use GCC's heavyweight implementation with runtime code generation or lightweight implementations by enhancing GCC;however, compiler-based implementations are poor in portability. In this study, we implement and evaluate more portable Tascell frameworks called "Tascell/SC" by using transformation-based portable implementations of nested functions. In addition, we propose Tascell-inspired portable frameworks only in C++ called "Tascell++" by using lambda expressions in C++11 for legitimate execution stack access.
In order to realize efficient fault recognition and utilization of the high-speed train (EMU) undercarriage image obtained by detection robot, image alignment technology play an important role. Firstly, research the o...
详细信息
Data in form of images is available everywhere in abundance. these images may always not be seeming to give all the relevant information from the naked eye. Many techniques have developed over time, to improve the qua...
详细信息
Interms of applications, chip technology is now growing quite quickly. Even though the use of chips has increased, there are still drawbacks like delay and chip complexity. Kogge-Stone Adder is sufficient to increase ...
详细信息
Sieving algorithms currently represent the fastest approach of solving the Shortest Vector Problem (SVP). However, current sieving algorithms exclusively utilize either CPUs or GPUs. this paper introduces a novel siev...
详细信息
ISBN:
(纸本)9789819790524;9789819790531
Sieving algorithms currently represent the fastest approach of solving the Shortest Vector Problem (SVP). However, current sieving algorithms exclusively utilize either CPUs or GPUs. this paper introduces a novel sieving approach tailored to CPU+GPU heterogeneous computing platforms. We constructed a runtime system capable of concurrently executing both CPU and GPU versions of the sieving algorithm. the GPU version of the sieving algorithm reduces the demand for graphics memory by efficiently transferring data in batches. We used two computing platforms to evaluate our method: Hannibal is equipped with an AMD Ryzen 7 5800H CPU and an NVIDIA RTX 3060 GPU;Zeus is equipped with an Intel Xeon Platinum 8176M CPU and two Integrated Matrox G200eW3 Graphics Controllers. the experimental results show that, compared to the classical sieving algorithm implementation in G6K, the proposed method achieves a minimum speedup of 7.2x (for 30-dimensional SVP) and a maximum of 588x (for 120-dimensional SVP) on Hannibal and a minimum speedup of 4.3x (for 30-dimensional SVP) and a maximum of 1230x (for 120-dimensional SVP) on Zeus.
With importance of data value is approved, data-sharing will create more and greater value has become consensus. However, data exchange has to use a trusted third party(TTP) as an intermediary in an untrusted network ...
详细信息
the proceedings contain 98 papers. the topics discussed include: linguistic-based data augmentation approach for offensive language detection;a mixed reality interface for tactical data management in geographic inform...
ISBN:
(纸本)9781665470100
the proceedings contain 98 papers. the topics discussed include: linguistic-based data augmentation approach for offensive language detection;a mixed reality interface for tactical data management in geographic information systems;the effect of statistical attributes on the determination of stock trading actions;reverse ant colony optimization for the winner determination problem in combinatorial auctions;brain computer interaction and cybersecurity of the brain;an anomaly detection study for the smart home environment;what does industry suggest to academia on software engineering education?;anomaly pattern analysis based on machine learning on real telecommunication data;explainable ai for software defect prediction with gradient boosting classifier;data augmentation of morphological brain network using multi-variate normal distribution;applying web crawler technologies for compiling parallel corpora as one stage of natural language processing;comparison of heuristic and metaheuristic algorithms;and a new algorithm for the initial feasible solutions of fixed charge transportation problem.
暂无评论