Minimizing the Effect of Sleep Deprivation in the Forward-Forward Algorithm

arXiv:2609.06042v1 Announce Type: new Abstract: This paper addresses the challenge posed by sleep deprivation in the Forward-Forward algorithm, where separating the two passes in this algorithm and imbalancing the data processing in the passes is considered an imitation of the cognitive processes observed in humans suffering from sleep deprivation. Previous research has demonstrated that sleep deprivation in the Forward-Forward algorithm has a catastrophic effect on learning efficacy. To mitigate this issue, we explore several approaches; these include alternative activation, optimized loss function, and threshold tuning. To simulate periodic rest, we reduce the number of positive passes in alternating epochs, creating short break phases. We additionally investigate the potential of caffeine-induced stimulation to enhance performance during sleep-deprived conditions. Experimental evaluations conducted on the MNIST and Fashion-MNIST datasets demonstrate that these modifications improve accuracy under the context of sleep deprivation. For example, a 2%-62% accuracy gain is observed in a severe sleep deprivation setting (16 positive or awake periods and 1 negative or sleep period). The approaches also enhance the resilience of the algorithm and its alignment with the adaptive mechanisms of human cognition.

Abstract:This paper addresses the challenge posed by sleep deprivation in the Forward-Forward algorithm, where separating the two passes in this algorithm and imbalancing the data processing in the passes is considered an imitation of the cognitive processes observed in humans suffering from sleep deprivation. Previous research has demonstrated that sleep deprivation in the Forward-Forward algorithm has a catastrophic effect on learning efficacy. To mitigate this issue, we explore several approaches; these include alternative activation, optimized loss function, and threshold tuning. To simulate periodic rest, we reduce the number of positive passes in alternating epochs, creating short break phases. We additionally investigate the potential of caffeine-induced stimulation to enhance performance during sleep-deprived conditions. Experimental evaluations conducted on the MNIST and Fashion-MNIST datasets demonstrate that these modifications improve accuracy under the context of sleep deprivation. For example, a 2%-62% accuracy gain is observed in a severe sleep deprivation setting (16 positive or awake periods and 1 negative or sleep period). The approaches also enhance the resilience of the algorithm and its alignment with the adaptive mechanisms of human cognition.

14 pages, 6 figures, 7 tables. Accepted at the 28th International Conference on Pattern Recognition (ICPR 2026), Lyon, France, August 17-22, 2026. This is the accepted manuscript; the Version of Record is published by Springer in Lecture Notes in Computer Science and is available online at this https URL

Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)

arXiv:2609.06042 [cs.LG]

(or arXiv:2609.06042v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.06042 arXiv-issued DOI via DataCite (pending registration)

Pattern Recognition. ICPR 2026. Lecture Notes in Computer Science, pp. 590-604. Springer, Cham (2026)

https://doi.org/10.1007/978-3-032-31933-3_40 DOI(s) linking to related resources

analiza aiqbench

Minimizing the Effect of Sleep Deprivation in the Forward-Forward Algorithm

Subiecte conexe