计算机科学
人工神经网络
人工智能
破译
认知
稳健性(进化)
模块化(生物学)
信息处理
机器学习
心理学
神经科学
遗传学
生物化学
生物
基因
化学
作者
Paul Blažek,Milo M. Lin
标识
DOI:10.1038/s43588-021-00132-w
摘要
The success of deep neural networks suggests that cognition may emerge from indecipherable patterns of distributed neural activity. Yet these networks are pattern-matching black boxes that cannot simulate higher cognitive functions and lack numerous neurobiological features. Accordingly, they are currently insufficient computational models for understanding neural information processing. Here, we show how neural circuits can directly encode cognitive processes via simple neurobiological principles. To illustrate, we implemented this model in a non-gradient-based machine learning algorithm to train deep neural networks called essence neural networks (ENNs). Neural information processing in ENNs is intrinsically explainable, even on benchmark computer vision tasks. ENNs can also simulate higher cognitive functions such as deliberation, symbolic reasoning and out-of-distribution generalization. ENNs display network properties associated with the brain, such as modularity, distributed and localist firing, and adversarial robustness. ENNs establish a broad computational framework to decipher the neural basis of cognition and pursue artificial general intelligence.
科研通智能强力驱动
Strongly Powered by AbleSci AI