Depthwise Separable Convolution 11-08-2021 11-08-2021 blog 7 minutes read (About 1018 words)Reducing Memory and Math Bandwidth Requirements for Convolution Deep Learning, Mathematics Read More
Multi-Thread Single-Stream VS Single-Thread Multi-Stream CUDA 10-18-2021 05-12-2022 blog 13 minutes read (About 1946 words)CUDA Programming Choices for CUDA Stream Deep Learning, Mathematics, CUDA, High Performance Computing, Computer Architecture, Parallel Computing Read More
Math-Bound VS Memory-Bound Operations 10-11-2021 09-18-2023 blog 8 minutes read (About 1188 words)Computation Bandwidth, Memory Bandwidth, and Data Reuse Deep Learning, Mathematics, Computer Architecture Read More
Fast Fourier Transform for Convolution 10-04-2021 09-20-2022 blog 9 minutes read (About 1346 words)Understand Asymptotically Faster Convolution Using Fast Fourier Transform Deep Learning, Mathematics Read More
Cross-Correlation VS Convolution 09-27-2021 09-27-2021 blog 6 minutes read (About 903 words)A Historical Ambiguity in Deep Learning Deep Learning, Mathematics Read More
Creating and Modifying ONNX Model Using ONNX Python API 09-15-2021 09-15-2021 blog 12 minutes read (About 1866 words)Getting Familiar with ONNX Data Structure and Python API Usages Deep Learning, ONNX Read More
Convolution and Transposed Convolution as Matrix Multiplication 09-08-2021 09-08-2021 blog 10 minutes read (About 1514 words)Understand Convolution and Transposed Convolution from a Different View Deep Learning Read More
ResNet CIFAR Classification Using LibTorch C++ API 07-01-2021 07-01-2021 blog 6 minutes read (About 837 words)User Experience on LibTorch C++ API Machine Learning, CPP, Deep Learning, PyTorch, LibTorch Read More
Neural Network 1 x 1 Convolution Horizontal Fusion 05-20-2021 05-20-2021 blog 6 minutes read (About 945 words)Mathematical Foundations for $1 \times 1$ Convolution Horizontal Fusion Deep Learning Read More
Neural Network Batch Normalization Fusion 05-10-2021 08-14-2022 blog 14 minutes read (About 2050 words)Mathematical Foundations for Batch Normalization Fusion Deep Learning Read More
Non-Autoregressive Model and Non-Autoregressive Decoding for Sequence to Sequence Tasks 04-27-2021 04-27-2021 blog 19 minutes read (About 2780 words)Enable Parallelized Non-Autoregressive Decoding Process for Sequence to Sequence Tasks Machine Learning, Deep Learning Read More
Autoregressive Model and Autoregressive Decoding for Sequence to Sequence Tasks 04-26-2021 04-26-2021 blog 17 minutes read (About 2523 words)Understand Autoregressive Models for Sequence to Sequence Tasks Machine Learning, Deep Learning Read More