Synaptic plasticity poses itself as a powerful method of self-regulated unsupervised learning in neural networks. A recent resurgence of interest has developed in utilizing Artificial Neural Networks (ANNs) together with synaptic plasticity for intra-lifetime learning. Plasticity has been shown to improve the learning capabilities of these networks in generalizing to novel environmental circumstances. However, the long-term stability of these trained networks has yet to be examined. This work demonstrates that utilizing plasticity together with ANNs leads to instability beyond the pre-specified lifespan used during training. This instability can lead to the dramatic decline of reward seeking behavior, or quickly lead to reaching environment terminal states. This behavior is shown to hold consistent for several plasticity rules on two different environments across many training time-horizons: a cart-pole balancing problem and a quadrupedal locomotion problem. We present a solution to this instability through the use of spiking neurons.
翻译:神经网络中自律的、不受监督的自控学习的强大方法是合成塑料。最近人们开始对利用人工神经网络(ANNs)的兴趣重新抬头,同时对生命周期内学习的合成塑料也产生了兴趣。可塑性已经证明提高了这些网络的学习能力,使之适应新的环境环境环境。然而,这些经过培训的网络的长期稳定性仍有待于研究。这项工作表明,与非本国网络一起使用可塑性会导致超出培训期间使用的特定寿命的不稳定性。这种不稳定性可能导致寻求行为奖赏的急剧下降,或迅速导致进入环境终点国家。这一行为表明,在许多培训时间-正数的不同环境中,对两种不同的环境都坚持了几条可塑性规则:一个马车极平衡问题和一个四分立的血管问题。我们通过使用螺旋神经元,为这种不稳定性提供了一种解决办法。