期刊
SENSORS
卷 21, 期 8, 页码 -出版社
MDPI
DOI: 10.3390/s21082678
关键词
spiking neural networks; STDP; learning; neurorobotics; cognitive maps; vector field of synaptic connections; vector field of functional connections
资金
- Ministry of Science and Higher Education of the Russian Federation [075-15-2020-808]
- Spanish Ministry of Science, Innovation [FIS2017-82900P]
The study introduces a spiking neural network capable of generating an internal representation of the external environment and implementing spatial memory, with the network's function explored through its embodiment in a robot moving in an arena with safe and dangerous zones.
Cognitive maps and spatial memory are fundamental paradigms of brain functioning. Here, we present a spiking neural network (SNN) capable of generating an internal representation of the external environment and implementing spatial memory. The SNN initially has a non-specific architecture, which is then shaped by Hebbian-type synaptic plasticity. The network receives stimuli at specific loci, while the memory retrieval operates as a functional SNN response in the form of population bursts. The SNN function is explored through its embodiment in a robot moving in an arena with safe and dangerous zones. We propose a measure of the global network memory using the synaptic vector field approach to validate results and calculate information characteristics, including learning curves. We show that after training, the SNN can effectively control the robot's cognitive behavior, allowing it to avoid dangerous regions in the arena. However, the learning is not perfect. The robot eventually visits dangerous areas. Such behavior, also observed in animals, enables relearning in time-evolving environments. If a dangerous zone moves into another place, the SNN remaps positive and negative areas, allowing escaping the catastrophic interference phenomenon known for some AI architectures. Thus, the robot adapts to changing world.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据