Global Navigation Satellite System (GNSS) provides a wide range of services. In highly dynamic environments, satellite signals are often corrupted by noise during transmission, and thermal noise in the receiver introd...
详细信息
The tilt system is the key part of the converter steelmaking, its function is to ensure the furnace can stop at any Angle. Due to the problem of excessive gear engagement gap between frequent starting and braking and ...
详细信息
As a basic subtask in natural language processing, text enunciation recognition aims at determining the enunciation relationship between presupposition and hypothesis. At present, most deep learning text sensitivity m...
详细信息
The Nano-Hyperspec spectrometer was used to preprocess Mikania micrantha images, such as geometric correction, image denoising, radiation correction and bad band elimination. The optimal exponential coefficient method...
详细信息
With the growing prevalence of service robots across various sectors, there is a growing need to ensure seamless connectivity between robots and users from virtually anywhere in the world. This demand has driven exten...
详细信息
Neural networks (NNs) have been successfully deployed in various fields. In NNs, a large number of multiply-accumulate (MAC) operations need to be performed. Most existing digital hardware platforms rely on parallel M...
详细信息
ISBN:
(纸本)9798350393545
Neural networks (NNs) have been successfully deployed in various fields. In NNs, a large number of multiply-accumulate (MAC) operations need to be performed. Most existing digital hardware platforms rely on parallel MAC units to accelerate these MAC operations. However, under a given area constraint, the number of MAC units in such platforms is limited, so MAC units have to be reused to perform MAC operations in a neural network. Accordingly, the throughput in generating classification results is not high, which prevents the application of traditional hardware platforms in extreme-throughput scenarios. Besides, the power consumption of such platforms is also high, mainly due to data movement. To overcome this challenge, in this paper, we propose to flatten and implement all the operations at neurons, e.g., MAC and ReLU, in a neural network with their corresponding logic circuits. To improve the throughput and reduce the power consumption of such logic designs, the weight values are embedded into the MAC units to simplify the logic, which can reduce the delay of the MAC units and the power consumption incurred by weight movement. The retiming technique is further used to improve the throughput of the logic circuits for neural networks. In addition, we propose a hardware-aware training method to reduce the area of logic designs of neural networks. Experimental results demonstrate that the proposed logic designs can achieve high throughput and low power consumption for several high-throughput applications.
In the era of ubiquitous digital information, question-answering systems have become indispensable tools for accessing and extracting knowledge from vast datasets. This research explores the design, implementation, an...
详细信息
Aiming at the problems of insufficient feature extraction and inaccurate prediction in existing aircraft engines remaining useful life prediction algorithms, a fusion model based on feature attention mechanism, stacke...
详细信息
Facial expression recognition (FER) is a critical task in intelligent educational technologies, enabling adaptive learning environments to respond to learners' emotional states and support more personalized instru...
详细信息
Along with the rapid development of user-side distributed power generation technology, it has become an important development trend to improve the reliability and economy of community energy use through the configurat...
详细信息
暂无评论