Leveraging conscious and nonconscious learning for efficient AI

Frontiers in Computational Neuroscience

Neuroscience

Susan Schneider¹  L. Andrew Coward²  Rachel St. Clair³ 

[1] Center for Future Mind, College of Arts and Letters, Florida Atlantic University, Boca Raton, FL, United States;College of Engineering and Computer Science, Australian National University, Canberra, ACT, Australia;Simuli Inc., Delray Beach, FL, United States;

关键词: the recommendation architecture;    deep learning;    consciousness;    novelty;    feedback;    resource constraints;    artificial intelligence;   

DOI  :  10.3389/fncom.2023.1090126

 received in 2022-11-04, accepted in 2023-03-06,  发布年份 2023

来源: Frontiers

【 摘 要 】

Various interpretations of the literature detailing the neural basis of learning have in part led to disagreements concerning how consciousness arises. Further, artificial learning model design has suffered in replicating intelligence as it occurs in the human brain. Here, we present a novel learning model, which we term the “Recommendation Architecture (RA) Model” from prior theoretical works proposed by Coward, using a dual-learning approach featuring both consequence feedback and non-consequence feedback. The RA model is tested on a categorical learning task where no two inputs are the same throughout training and/or testing. We compare this to three consequence feedback only models based on backpropagation and reinforcement learning. Results indicate that the RA model learns novelty more efficiently and can accurately return to prior learning after new learning with less computational resources expenditure. The final results of the study show that consequence feedback as interpretation, not creation, of cortical activity creates a learning style more similar to human learning in terms of resource efficiency. Stable information meanings underlie conscious experiences. The work provided here attempts to link the neural basis of nonconscious and conscious learning while providing early results for a learning protocol more similar to human brains than is currently available.

【 授权许可】

Unknown   
Copyright © 2023 St. Clair, Coward and Schneider.