March 14, 2024, 4:41 a.m. | Simone Scardapane, Alessandro Baiocchi, Alessio Devoto, Valerio Marsocci, Pasquale Minervini, Jary Pomponi

cs.LG updates on

arXiv:2403.07965v1 Announce Type: new
Abstract: This article summarizes principles and ideas from the emerging area of applying \textit{conditional computation} methods to the design of neural networks. In particular, we focus on neural networks that can dynamically activate or de-activate parts of their computational graph conditionally on their input. Examples include the dynamic selection of, e.g., input tokens, layers (or sets of layers), and sub-modules inside each layer (e.g., channels in a convolutional filter). We first provide a general formalism to …

abstract article arxiv computation computational cs.lg design examples focus graph ideas networks neural networks research trends type

Senior Data Engineer

@ Displate | Warsaw

Principal Software Engineer

@ Microsoft | Prague, Prague, Czech Republic

Sr. Global Reg. Affairs Manager

@ BASF | Research Triangle Park, NC, US, 27709-3528

Senior Robot Software Developer

@ OTTO Motors by Rockwell Automation | Kitchener, Ontario, Canada

Coop - Technical Service Hub Intern

@ Teradyne | Santiago de Queretaro, MX

Coop - Technical - Service Inside Sales Intern

@ Teradyne | Santiago de Queretaro, MX