• 0 Citations
20192019

Research output per year

If you made any changes in Pure these will be visible here soon.

Personal profile

Quote

Shiwei Liu is a first year Ph.D. researcher at the Mathematics and Computer Science department at the Eindhoven University of Technology. His Ph.D. topic is scalable deep learning. Recently, his research interest is compressing conventional deep artificial neural network models from the perspective of pruning, sparse and evolutionary training. He believes that sparse artificial neural networks have the potential to beat conventional dense networks both in performance and the ability to be applied to real applications. 

Fingerprint Dive into the research topics where Shiwei Liu is active. These topic labels come from the works of this person. Together they form a unique fingerprint.

Network Recent external collaboration on country level. Dive into details by clicking on the dots.

Research Output

  • 2 Article
  • 1 Conference contribution

Intrinsically sparse long short-term memory networks

Liu, S., Mocanu, D. & Pechenizkiy, M., 26 Jan 2019, In : arXiv. 9 p., 1901.09208v1.

Research output: Contribution to journalArticleAcademic

Open Access
File
  • 22 Downloads (Pure)

    On improving deep learning generalization with adaptive sparse connectivity

    Liu, S., Mocanu, D. & Pechenizkiy, M., 14 Jun 2019, ICML 2019 Workshop on Understanding and Improving General-ization in Deep Learning. 5 p. 1906.11626v1

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Open Access
    File
  • 7 Downloads (Pure)

    Sparse evolutionary deep learning with over one million artificial neurons on commodity hardware

    Liu, S., Mocanu, D., Ramapuram Matavalam, A. R., Pei, Y. & Pechenizkiy, M., 26 Jan 2019, In : arXiv. 14 p., 1901.09181v1.

    Research output: Contribution to journalArticleAcademic

    Open Access
    File
  • 13 Downloads (Pure)