K
Katarzyna Janocha
Researcher at Jagiellonian University
Publications - 3
Citations - 581
Katarzyna Janocha is an academic researcher from Jagiellonian University. The author has contributed to research in topics: Deep learning & Computer science. The author has an hindex of 2, co-authored 2 publications receiving 399 citations.
Papers
More filters
Journal ArticleDOI
On Loss Functions for Deep Neural Networks in Classification
TL;DR: This paper investigates how particular choices of loss functions affect deep models and their learning dynamics, as well as resulting classifiers robustness to various effects, and shows that L1 and L2 losses are justified classification objectives for deep nets, by providing probabilistic interpretation in terms of expected misclassification.
Posted Content
On Loss Functions for Deep Neural Networks in Classification
TL;DR: In this paper, the authors investigate how particular choices of loss functions affect deep models and their learning dynamics, as well as resulting classifiers robustness to various effects, and show that L1 and L2 losses are, quite surprisingly, justified classification objectives for deep nets, by providing probabilistic interpretation in terms of expected misclassification.
Journal ArticleDOI
TwERC: High Performance Ensembled Candidate Generation for Ads Recommendation at Twitter
Vanessa Cai,Pradeep Prabakar,Manuel Serrano Rebuelta,Lucas Rosen,Federico Monti,Katarzyna Janocha,Tomo Lazovich,J. Raj,Yedendra B. Shrinivasan,Hao Li,Thomas Markovich +10 more
TL;DR: In this paper , a machine learning first heterogeneous re-architecture of the candidate generation phase of a large-scale ad recommendation problem is presented, where a real-time light ranker is combined with sourcing strategies capable of capturing additional information.