LODeNNS: A Linearly-approximated and Optimized Dendrocentric Nearest Neighbor STDP

LODeNNS: A Linearly-approximated and Optimized Dendrocentric Nearest Neighbor STDP
复制标题

LODeNNS:线性近似和优化的树心最近邻 STDP

DOI:
10.1145/3546790.3546793
复制
发表时间:
2022
期刊:
ICONS '22: Proceedings of the International Conference on Neuromorphic Systems 2022
影响因子:
--
通讯作者:
Etienne-Cummings, Ralph
Etienne-Cummings, Ralph
中科院分区:
--
文献类型:
--
作者:
Akwaboah, Akwasi;Etienne-Cummings, Ralph

文献摘要

参考文献

相似文献

在大规模神经形态系统中实现赫布可塑性对于重新配置它们以执行识别任务至关重要。尖峰时间依赖性可塑性作为实现这一效果的工具,近年来受到了很多关注。这种现象将权重更新信息编码为突触前和突触后事件时间之间的相关性,因此,硅神经网络中的每个突触必须以某种方式保持自己的时间。我们提出了一种生物学上合理且优化的寄存器传输级别(RTL)和最近邻 STDP 算法方法,并由突触后树突处理时间管理。我们采用基于时间常数的斜坡近似,以便于 RTL 实现和合并到大规模数字神经形态系统中。
Realizing Hebbian plasticity in large-scale neuromorphic systems is essential for reconfiguring them for recognition tasks. Spike-timing-dependent plasticity, as a tool to this effect, has received a lot of attention in recent times. This phenomenon encodes weight update information as correlations between the presynaptic and postsynaptic event times, as such, it is imperative for each synapse in a silicon neural network to somehow keep its own time. We present a biologically plausible and optimized Register Transfer Level (RTL) and algorithmic approach to the Nearest-Neighbor STDP with time management handled by the postsynaptic dendrite. We adopt a time-constant based ramp approximation for ease of RTL implementation and incorporation in large-scale digital neuromorphic systems.
STDP 的组合数字逻辑方法
DOI: 10.1109/iscas.2011.5937655
发表时间: 2011
期刊: 2011 IEEE International Symposium of Circuits and Systems (ISCAS)
影响因子: --
作者:
A. Cassidy;A. Andreou;J. Georgiou
通讯作者: J. Georgiou
用于实时神经模拟的真实尖峰时序可塑性模型的数字映射
DOI: --
发表时间: 2009
期刊:
影响因子: --
作者:
B. Belhadj;J. Tomas;Y. Bornat;A. Daouzli;O. Malot;S. Renaud
通讯作者: S. Renaud