all AI news
Neural Redshift: Random Networks are not Random Functions
March 5, 2024, 2:42 p.m. | Damien Teney, Armand Nicolicioiu, Valentin Hartmann, Ehsan Abbasnejad
cs.LG updates on arXiv.org arxiv.org
Abstract: Our understanding of the generalization capabilities of neural networks (NNs) is still incomplete. Prevailing explanations are based on implicit biases of gradient descent (GD) but they cannot account for the capabilities of models from gradient-free methods nor the simplicity bias recently observed in untrained networks. This paper seeks other sources of generalization in NNs.
Findings. To understand the inductive biases provided by architectures independently from GD, we examine untrained, random-weight networks. Even simple MLPs show …
abstract arxiv bias biases capabilities cs.ai cs.cv cs.lg free functions gradient networks neural networks nns paper random redshift simplicity type understanding
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Risk Management - Machine Learning and Model Delivery Services, Product Associate - Senior Associate-
@ JPMorgan Chase & Co. | Wilmington, DE, United States
Senior ML Engineer (Speech/ASR)
@ ObserveAI | Bengaluru