首页> 外文会议>International conference on the simulation and synthesis of living systems >Evolutionary Advantages of Neuromodulated Plasticity in Dynamic, Reward-based Scenarios
【24h】

Evolutionary Advantages of Neuromodulated Plasticity in Dynamic, Reward-based Scenarios

机译:动态,基于奖励的场景中神经调节可塑性的进化优势

获取原文

摘要

Neuromodulation is considered a key factor for learning and memory in biological neural networks. Similarly, artificial neural networks could benefit from modulatory dynamics when facing certain types of learning problem. Here we test this hypothesis by introducing modulatory neurons to enhance or dampen neural plasticity at target neural nodes. Simulated evolution is employed to design neural control networks for T-maze learning problems, using both standard and modulatory neurons. The results show that experiments where modulatory neurons are enabled achieve better learning in comparison to those where modulatory neurons are disabled. We conclude that modulatory neurons evolve autonomously in the proposed learning tasks, allowing for increased learning and memory capabilities.
机译:神经调节被认为是生物神经网络中学习和记忆的关键因素。同样,当面对某些类型的学习问题时,人工神经网络可能会受益于调制动力学。在这里,我们通过引入调节性神经元来增强或减弱目标神经节点的神经可塑性来检验该假设。模拟进化用于使用标准神经元和调制神经元设计用于T迷宫学习问题的神经控制网络。结果表明,与禁用调节神经元的实验相比,启用了调节神经元的实验可获得更好的学习效果。我们得出的结论是,调制神经元在拟议的学习任务中自主进化,从而增加了学习和记忆能力。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号