Feb. 15, 2024, 5:42 a.m. | Loek van Rossem, Andrew M. Saxe

cs.LG updates on arXiv.org arxiv.org

arXiv:2402.09142v1 Announce Type: new
Abstract: Deep neural networks come in many sizes and architectures. The choice of architecture, in conjunction with the dataset and learning algorithm, is commonly understood to affect the learned neural representations. Yet, recent results have shown that different architectures learn representations with striking qualitative similarities. Here we derive an effective theory of representation learning under the assumption that the encoding map from input to hidden representation and the decoding map from representation to output are arbitrary …

abstract algorithm architecture architectures arxiv cs.lg dataset dynamics learn networks neural networks q-bio.nc representation representation learning type

Doctoral Researcher (m/f/div) in Automated Processing of Bioimages

@ Leibniz Institute for Natural Product Research and Infection Biology (Leibniz-HKI) | Jena

Seeking Developers and Engineers for AI T-Shirt Generator Project

@ Chevon Hicks | Remote

Principal Research Engineer - Materials

@ GKN Aerospace | Westlake, TX, US

Internship in Data and Projects

@ Bosch Group | Mechelen, Belgium

Research Scientist- Applied Mechanics

@ Corning | Pune, MH, IN, 410501

Product Data Analyst

@ AUTODOC | Lisbon-remote