This work explores an efficient convolutional acceleration framework tailored for edge devices by integrating Depthwise Convolution with the Winograd algorithm. Through RTL-based hardware ...

Abstract: Aiming at the problem that mainlobe distortion and peak offset caused by mainlobe interference in wideband beamforming, a mainlobe maintenance (MM) wideband beamforming algorithm based on ...

Abstract: The main drawback of the second-order Volterra (SOV) filter is that its coefficients increase exponentially with the length of the memory, which has promoted the development of ...

Many-core neuromorphic integrated circuits (ICs) have the potential advantages of low power consumption, high parallelism, etc. for the edge computing of deep learning. A key problem in the ...

Abstract: Autonomous vehicles require highly reliable collision-free capabilities, necessitating extensive research in path planning. Path planning determines an optimal path, crucial for safe and ...