Lilun Zhang

Publications54
h-index11
Citations483
Highly Influential Citations18
Claim Author Page
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • Chuangxia Huang
  • 156 Publications • 3,866 Citations
  • Yongxian Wang
  • 52 Publications • 224 Citations
  • T. Virtanen
  • 313 Publications • 12,089 Citations
  • Mark D. Plumbley
  • 418 Publications • 10,575 Citations
  • Publications
  • Influence
Test-driving Intel Xeon Phi
TLDR
The experience indicates that a simple data structure and massive parallelism are critical for Xeon Phi to perform well, and when compiler-driven parallelization and/or vectorization fails, programming Xeon Phi for performance can become very challenging.
View on ACM
Mixup-Based Acoustic Scene Classification Using Multi-Channel Convolutional Neural Network
TLDR
This paper explores the use of Multi-channel CNN for the classification task, which aims to extract features from different channels in an end-to-end manner, and explores the using of mixup method, which can provide higher prediction accuracy and robustness in contrast with previous models.
View PDF on arXiv
An Empirical Study of Intel Xeon Phi
TLDR
This paper micro-benchmarked the main hardware components of Xeon Phi, and shows that, in ideal microbenchmarking conditions, the performance that can be achieved is very close to the theoretical peak, as given in the official programmer's guide.
View PDF on arXiv
Collaborating CPU and GPU for large-scale high-order CFD simulations with complex grids on the TianHe-1A supercomputer
View via Publisher
Performance optimizations for scalable CFD applications on hybrid CPU+MIC heterogeneous computing system with millions of cores
View PDF on arXiv
Environmental Sound Classification Based on Multi-temporal Resolution Convolutional Neural Network Combining with Multi-level Features
TLDR
Results demonstrate that the proposed method is highly effective in the classification tasks by employing multi-temporal resolution and multi-level features, and it outperforms the previous methods which only account for single- level features.
View PDF on arXiv
Large-Scale Whale-Call Classification by Transfer Learning on Multi-Scale Waveforms and Time-Frequency Features
TLDR
An effective data-driven approach based on pre-trained Convolutional Neural Networks using multi-scale waveforms and time-frequency feature representations is developed in order to perform the classification of whale calls from a large open-source dataset recorded by sensors carried by whales.
View PDF
Benchmarking Intel Xeon Phi to Guide Kernel Design
TLDR
Four hardware-centric guidelines and a machine model for Xeon Phi programmers in search for performance are presented and it is shown that, in ideal microbenchmarking conditions, the achieved performance is very close to the theoretical one as given in the official programmer's guide.
Acoustic Scene Classification Based on Dense Convolutional Networks Incorporating Multi-channel Features
View via Publisher
Efficient parallel implementation of large scale 3D structured grid CFD applications on the Tianhe-1A supercomputer
View via Publisher
...
...