arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.10359cs.NEcs.AI
收藏

用于多任务处理的、具备高级活动依赖性的进化式发育人工神经网络

Evolved Developmental Artificial Neural Networks for Multitasking with Advanced Activity Dependence

Rose-Hulman Institute of Technology(罗斯霍曼理工学院)

Yintong Zhang, Jason A. Yoder

AI总结:

本研究针对带活动依赖性的发育人工神经网络多任务学习问题,扩展了活动依赖性的作用参数范围,显著提升了网络性能,为相关研究提供了新方向。

摘要:

近年来,笛卡尔遗传规划(Cartesian Genetic Programming)已被用于进化发育程序,以引导人工神经网络(ANNs)的形成。该方法已被证明能够成功让人工神经网络执行多项任务,同时避免灾难性遗忘。该方法的一个独特之处在于,它使用经过进化的独立发育程序来调控独立胞体单元和树突单元的发育。这种方法带来的一个契机是,能够将活动依赖性(Activity Dependence,AD)整合到模型中,从而让环境反馈可以帮助调控每类单元的行为。此前的研究表明,有限版本的AD(仅影响神经偏置)相较于无AD的人工神经网络仅能带来边际提升。在本研究中,我们展示了对AD进行新扩展后得到的可观结果。具体而言,我们证明,将AD应用于包括健康度和位置在内的新神经参数,以及将所有这些参数与偏置结合应用时,能带来更显著的性能提升。我们阐述了本研究的意义,并提出了几个有前景的未来研究方向。

英文摘要:

Recently, Cartesian Genetic Programming has been used to evolve developmental programs to guide the formation of artificial neural networks (ANNs). This approach has demonstrated success in enabling ANNs to perform multiple tasks while avoiding catastrophic forgetting. One unique aspect of this approach is the use of separate developmental programs evolved to regulate the development of separate soma and dendrite units. An opportunity afforded by this approach is the ability to incorporate Activity Dependence (AD) into the model such that environmental feedback can help to regulate the behavior of each type of unit. Previous work has shown a limited version of AD (influencing neural bias) to provide marginal improvements over non-AD ANNs. In this work, we present promising results from new extensions to AD. Specifically, we demonstrate a more significant improvement via AD on new neural parameters including health and position, as well as a combination of all of these along with bias. We report on the implications of this work and suggest several promising directions for future work.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑