all AI news
Associative Memories in the Feature Space
Feb. 19, 2024, 5:42 a.m. | Tommaso Salvatori, Beren Millidge, Yuhang Song, Rafal Bogacz, Thomas Lukasiewicz
cs.LG updates on arXiv.org arxiv.org
Abstract: An autoassociative memory model is a function that, given a set of data points, takes as input an arbitrary vector and outputs the most similar data point from the memorized set. However, popular memory models fail to retrieve images even when the corruption is mild and easy to detect for a human evaluator. This is because similarities are evaluated in the raw pixel space, which does not contain any semantic information about the images. This …
abstract arxiv corruption cs.cv cs.lg data easy feature function images memories memory popular set space type vector
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
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
AI Engineer Intern, Agents
@ Occam AI | US