Search Results for author:
Found 2 papers, 0 papers with code
Compiler-Level Matrix Multiplication Optimization for Deep Learning
Compiler-level optimization of GEMM has significant performance impact on training and executing deep learning models.
Gradient-Coherent Strong Regularization for Deep Neural Networks
However, we observe that imposing strong L1 or L2 regularization with stochastic gradient descent on deep neural networks easily fails, which limits the generalization ability of the underlying neural networks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
