Intelligent and Interactive Systems

User Tools

Site Tools


people:david

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Next revision Both sides next revision
people:david [2021/01/02 17:29]
David Peer [PhD Student]
people:david [2022/02/16 09:10]
David Peer
Line 3: Line 3:
 ==== PhD Student ==== ==== PhD Student ====
  
-David Peer is currently ​PhD student in the Intelligent and Interactive System group at the Universität Innsbruck (Austria) under the supervision of Antonio Rodriguez-Sanchez and is working at DeepOpinion as Machine Learning ResearcherHe obtained the degree of M.Sc and B.Sc in Computer Science at the Universität Innsbruck (Austria) and studies ​currently the gap between expressivity and learnability of neural networks, especially ​for Natural language processing (NLP) models.+I'​m ​Ph.D. student in the Intelligent and Interactive System group at the Universität Innsbruck (Austria) under the supervision of Antonio Rodriguez-Sanchez and I'​m ​working at DeepOpinion as a machine learning researcherobtained the degree of M.Sc and B.Sc in Computer Science at the Universität Innsbruck (Austria) and study currently the gap between expressivity and learnability of neural networks. At DeepOpinion I study how we can transform this knowledge into novel AutoML or Neural Architecture Search (NAS) algorithms ​for Natural language processing (NLP) models ​to outperform current SOTA methods.
  
 [[https://​scholar.google.com/​citations?​user=THmkZOIAAAAJ|Google Scholar]] [[https://​scholar.google.com/​citations?​user=THmkZOIAAAAJ|Google Scholar]]
Line 17: Line 17:
 === Areas of Interest === === Areas of Interest ===
 ---- ----
-  * Understanding ​the gap between expressivity and learnability of neural networks ​([[https://​arxiv.org/​abs/​1905.08744|1]],​ [[https://​arxiv.org/​abs/​2011.02956|2]])\\ +My main interest is to improve state-of-the art results in machine-learning by understanding ​the gap between expressivity and learnability of neural networks ​that seems to be huge. Here is a list of the publications in this research direction where I'm first- or co-author where we used different theoretically motivated algorithms to improve SOTA: [[https://​arxiv.org/​abs/​1905.08744|1]],​ [[https://​arxiv.org/​abs/​2011.02956|2]], [[https://​preregister.science/​papers_20neurips/​55_paper.pdf|3]], ​[[https://​www.sciencedirect.com/science/article/pii/S2665963821000014|4]], [[https://​arxiv.org/​abs/​2103.04331|5]][[https://​arxiv.org/​abs/​2102.11944|6]][[https://​arxiv.org/​abs/​2105.14839|7]] [[https://​arxiv.org/​abs/​2104.07393|8]] [[https://​arxiv.org/​abs/​2201.11091|9]]\\
-  * Topics: [[https://​www.cs.huji.ac.il/~shais/UnderstandingMachineLearning/|Learning Theory]], Deep LearningMachine Learning, Natural language processing \\ +
-  * HobbiesClimbinghiking, snowboarding etc.+
  
 === Positions === === Positions ===
 ----  ---- 
-09.2019 - Today   | Researcher at University of Innsbruck (IIS group) \\+01.2020 - Today   | Machine Learning Researcher at DeepOpinion \\ 
 +09.2019 - 12.2020 ​| Researcher at University of Innsbruck (IIS group) \\
 02.2019 - 09.2019 | Researcher at University of Innsbruck (DPS group) \\ 02.2019 - 09.2019 | Researcher at University of Innsbruck (DPS group) \\
 04.2012 - 08.2018 | Software Developer at World-Direct eBusiness Solutions \\ 04.2012 - 08.2018 | Software Developer at World-Direct eBusiness Solutions \\
people/david.txt · Last modified: 2023/04/19 15:34 by David Peer