April 22, 2024, 4:42 a.m. | Lu\'is Carvalho, Jo\~ao L. Costa, Jos\'e Mour\~ao, Gon\c{c}alo Oliveira

cs.LG updates on arXiv.org arxiv.org

arXiv:2404.12928v1 Announce Type: new
Abstract: The Neural Tangent Kernel (NTK) has emerged as a fundamental concept in the study of wide Neural Networks. In particular, it is known that the positivity of the NTK is directly related to the memorization capacity of sufficiently wide networks, i.e., to the possibility of reaching zero loss in training, via gradient descent. Here we will improve on previous works and obtain a sharp result concerning the positivity of the NTK of feedforward networks of …

abstract arxiv capacity concept cs.ai cs.lg fundamental kernel loss math.pr math.sp networks neural networks possibility study type

Data Engineer

@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York