Search Results for author:
Found 7 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.
Adversarial Sampling and Training for Semi-Supervised Information Retrieval
To solve the problems at the same time, we propose an adversarial sampling and training framework to learn ad-hoc retrieval models with implicit feedback.
Sequenced-Replacement Sampling for Deep Learning
We propose sequenced-replacement sampling (SRS) for training deep neural networks.
Interpreting Deep Classifier by Visual Distillation of Dark Knowledge
Interpreting black box classifiers, such as deep networks, allows an analyst to validate a classifier before it is deployed in a high-stakes setting.
Achieving Strong Regularization for Deep Neural Networks
L1 and L2 regularizers are critical tools in machine learning due to their ability to simplify solutions.
