Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Zhi-Gang Liu

Zhi-Gang Liu

Efficient Residue Number System Based Winograd Convolution

Jul 23, 2020
Zhi-Gang Liu, Matthew Mattina

Figure 1 for Efficient Residue Number System Based Winograd Convolution

Figure 2 for Efficient Residue Number System Based Winograd Convolution

Figure 3 for Efficient Residue Number System Based Winograd Convolution

Figure 4 for Efficient Residue Number System Based Winograd Convolution

* Accepted by ECCV2020 Conference

Access Paper or Ask Questions

Systolic Tensor Array: An Efficient Structured-Sparse GEMM Accelerator for Mobile CNN Inference

May 16, 2020
Zhi-Gang Liu, Paul N. Whatmough, Matthew Mattina

Figure 1 for Systolic Tensor Array: An Efficient Structured-Sparse GEMM Accelerator for Mobile CNN Inference

Figure 2 for Systolic Tensor Array: An Efficient Structured-Sparse GEMM Accelerator for Mobile CNN Inference

Figure 3 for Systolic Tensor Array: An Efficient Structured-Sparse GEMM Accelerator for Mobile CNN Inference

Figure 4 for Systolic Tensor Array: An Efficient Structured-Sparse GEMM Accelerator for Mobile CNN Inference

* Accepted by IEEE Computer Architecture Letters on 3/4/2020

Access Paper or Ask Questions

Learning low-precision neural networks without Straight-Through Estimator(STE)

Mar 04, 2019
Zhi-Gang Liu, Matthew Mattina

Figure 1 for Learning low-precision neural networks without Straight-Through Estimator(STE)

Figure 2 for Learning low-precision neural networks without Straight-Through Estimator(STE)

Figure 3 for Learning low-precision neural networks without Straight-Through Estimator(STE)

Figure 4 for Learning low-precision neural networks without Straight-Through Estimator(STE)

Access Paper or Ask Questions