2021/06/15 by Wilkie Olin-Ammentorp, Olin-Ammentorp, Wilkie, Maxim Bazhenov +1
Engineering · Materials Science · #Advanced Memory and Neural Computing #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Machine Learning (cs.LG) #Machine Learning in Materials Science
paper · pdf · doi:10.48550/arxiv.2106.08446
openalex publication_date 2021/06/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Despite rapid progress, current deep learning methods face a number of critical challenges. These include high energy consumption, catastrophic forgetting, dependance on global losses, and an inability to reason symbolically. By combining concepts from information bottleneck theory and vector-symbolic architectures, we propose and implement a novel information processing architecture, the 'Bridge network.' We show this architecture provides unique advantages which can address the problem of global losses and catastrophic forgetting. Furthermore, we argue that it provides a further basis for increasing energy efficiency of execution and the ability to reason symbolically.