Neuromorphic Place Cells
A neuromorphic SLAM system shows potential for more efficient implementation than its traditional counterpart. We demonstrate a mixed-mode implementation for spatial encoding neurons including theta cells, vector cells, and place cells. Together, they form a biologically plausible network that could reproduce the localization functionality of place cells. The system consists of a theta chip with 128 units and an FPGA encoding 4 networks for vector cells formation that provides the capability for tracking on a 11 by 11 place cell grid. Experimental results validate the robustness of our model when suffering from 18% standard deviation from mathematical models induced by variations of analog circuits. We provide a foundation for implementing dynamic neuromorphic SLAM systems for nonhomogeneous mapping and inspirations for the formation of spatial cells in biology.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Mimicking associative learning of rats via a neuromorphic robot in open field maze using spatial cell models
Data-driven Artificial Intelligence (AI) approaches have exhibited remarkable prowess across various cognitive tasks using extensive training data. However, the reliance on large datasets and neural networks presents cha…
Improving Inference Lifetime of Neuromorphic Systems via Intelligent Synapse Mapping
Non-Volatile Memories (NVMs) such as Resistive RAM (RRAM) are used in neuromorphic systems to implement high-density and low-power analog synaptic weights. Unfortunately, an RRAM cell can switch its state after reading i…
BIG-bench Machine LearningPhilosophyOn the Mitigation of Read Disturbances in Neuromorphic Inference Hardware
Non-Volatile Memory (NVM) cells are used in neuromorphic hardware to store model parameters, which are programmed as resistance states. NVMs suffer from the read disturb issue, where the programmed resistance state drift…
Reliability-Performance Trade-offs in Neuromorphic Computing
Neuromorphic architectures built with Non-Volatile Memory (NVM) can significantly improve the energy efficiency of machine learning tasks designed with Spiking Neural Networks (SNNs). A major source of voltage drop in a …
BIG-bench Machine LearningHigher-Order Spatial Information for Self-Supervised Place Cell Learning
Mammals navigate novel environments and exhibit resilience to sparse environmental sensory cues via place and grid cells, which encode position in space. While the efficiency of grid cell coding has been extensively stud…
NavigateSelf-Supervised Learning