4 papers
A Non-sequential Approach to Deep User Interest Model for CTR Prediction
Keke Zhao, Xing Zhao, Qi Cao +1
Click-Through Rate (CTR) prediction plays an important role in many industrial applications, and recently a lot of attention is paid to the deep interest models which use attention…
Elastic Bulk Synchronous Parallel Model for Distributed Deep Learning
Xing Zhao, Manos Papagelis, Aijun An +3
The bulk synchronous parallel (BSP) is a celebrated synchronization model for general-purpose parallel computing that has successfully been employed for distributed training of mac…
Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings
Bao Xin Chen, Raghavender Sahdev, Dekun Wu +3
Scene Classification has been addressed with numerous techniques in computer vision literature. However, with the increasing number of scene classes in datasets in the field, it ha…
Dynamic Stale Synchronous Parallel Distributed Training for Deep Learning
Xing Zhao, Aijun An, Junfeng Liu +1
Deep learning is a popular machine learning technique and has been applied to many real-world problems. However, training a deep neural network is very time-consuming, especially o…