An memristor-based synapse implementation using BCM learning rule
نویسندگان
چکیده
A novel memristive synapse model based on the HP memristor is proposed in this paper, which can address problem of synaptic weight infinite modulations. The sliding threshold mechanism Bienenstock-Cooper-Munro rule (BCM) used to redefine memristance (i.e. weight) adjustment process model. Based memristor-based and Leaky Integrate-and-Fire neurons, a spiking neural network (SNN) hardware fragment constructed, where spike trains with different frequencies are evaluate stability performance SNN hardware. Results show that compared other approaches, stable under stimuli due characteristics model, prove able mimic biological behaviour modulations addressed.
منابع مشابه
Emergent Dynamical Properties of the BCM Learning Rule
The Bienenstock-Cooper-Munro (BCM) learning rule provides a simple setup for synaptic modification that combines a Hebbian product rule with a homeostatic mechanism that keeps the weights bounded. The homeostatic part of the learning rule depends on the time average of the post-synaptic activity and provides a sliding threshold that distinguishes between increasing or decreasing weights. There ...
متن کاملReinforcement Learning, Spike-Time-Dependent Plasticity, and the BCM Rule
Learning agents, whether natural or artificial, must update their internal parameters in order to improve their behavior over time. In reinforcement learning, this plasticity is influenced by an environmental signal, termed a reward, that directs the changes in appropriate directions. We apply a recently introduced policy learning algorithm from machine learning to networks of spiking neurons a...
متن کاملAdaptive Learning Rule for Hardware-based Deep Neural Networks Using Electronic Synapse Devices
In this paper, we propose a learning rule based on a back-propagation (BP) algorithm that can be applied to a hardware-based deep neural network (HW-DNN) using electronic devices that exhibit discrete and limited conductance characteristics. This adaptive learning rule, which enables forward, backward propagation, as well as weight updates in hardware, is helpful during the implementation of po...
متن کاملA Plausible Memristor Implementation of Deep Learning Neural Networks
A possible method for hardware implementation of multilayer neural networks with the back-propagation learning algorithm employing memristor cross-bar matrices for weight storage is modeled. The proposed approach offers an efficient way to perform both learning and recognition operations. The solution of several arising problems, such as the representation and multiplication of signals as well ...
متن کاملMemristor Bridge Synapse Application for Integrate and Fire and Hodgkin-Huxley Neuron Cell
Memory resistor or memristor is already fabricated successfully using current nano dimension technology. Based on its unique hysteresis, the amount of resistance remains constant over time, controlled by the time, the amplitude, and the polarity of the applied voltage. The unique hysteretic current-voltage characteristic in the memristor causes this element to act as a non-volatile resistive me...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Neurocomputing
سال: 2021
ISSN: ['0925-2312', '1872-8286']
DOI: https://doi.org/10.1016/j.neucom.2020.10.106