Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 4 of 4 for “"Winograd algorithm"”.
-
Techniques and Optimization Strategies for Efficient Hardware Acceleration of Neural Networks: Tap-Wisely-Quantized Winograd Algorithm and Capsule Networks
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Optimizing Convolutions in State-of-the-art Convolutional Neural Networks on Intel Xeon Phi
… multiplication formulation, FFT formulation, Winograd algorithm, and direct convolution. Interestingly, most of these implementations target GPU architecture, which is mainly due to - 1) higher theoretical peak FLOPs of GPU and 2) popularity of CUDA deep learning library. However, not much …
-
Optimization of Spatial Convolution in ConvNets on Intel KNL
… here was to use an unconventional convolution algorithm called Winograd Convolution algorithm to decrease the number of arithmetic operations. However, the reduction of arithmetic operations in Winograd algorithm comes at the cost of complicating the memory accesses. So the objective was to use …
-
An Introduction to the Winograd Discrete Fourier Transform
This paper illustrates Winograd's approach to computing the Discrete Fourier Transform (DFT). This new approach changes the DFT into a cyclic convolution of 2 sequences, and illustrates shortcuts for computing this cyclic convolution. This method is known to reduce the number of multiplies required …