Sleep Deprivation in the Forward-Forward Algorithm
This addresses a biological-inspired problem for machine learning researchers, but it appears incremental as it builds on the existing Forward-Forward algorithm.
The paper investigates how the separation between sleep and awake phases in the Forward-Forward algorithm affects learning, finding that the gap size influences capabilities and negative data helps mitigate sleep deprivation effects.
This paper aims to explore the separation of the two forward passes in the Forward-Forward algorithm from a biological perspective in the context of sleep. We show the size of the gap between the sleep and awake phase influences the learning capabilities of the algorithm and highlight the importance of negative data in diminishing the devastating effects of sleep deprivation.