Abstract
Neuromorphic computing has shown great advantages towards cognitive tasks with high speed and remarkable energy efficiency. Memristor is considered as one of the most promising candidates for the electronic synapse of the neuromorphic computing system due to its scalability, power efficiency and capability to simulate biological behaviors. Several memristor-based hardware demonstrations have been explored to achieve the capacity of unsupervised learning with the spike-rate-dependent plasticity (SRDP) learning rule. However, the learning capacity is limited and few of the memristor-based hardware demonstrations have explored the online unsupervised learning at the network level with an SRDP algorithm. Here, we construct a memristor-based hardware system and demonstrate the online unsupervised learning of SRDP networks. The neuromorphic system consists of multiple memristor arrays as the synapse and the discrete CMOS circuit unit as the neuron. Unsupervised learning and online weight update of 10 MNIST handwritten digits are realized by the constructed SRDP networks, and the recognition accuracy is above 90% with 20% device variation. This work paves the way towards the realization of large-scale and efficient networks for more complex tasks.
Highlights
The human brain is a highly efficient system, which consists of approximately 1011 neurons and 1015 synapses with merely 20 W power consumption [1–3]
Recent studies focus on unsupervised learning [25–30], where the synaptic weights are usually updated according to bio-inspired local learning rules [31–33], such as spiketiming-dependent plasticity (STDP) [34,35] and spike-rate-dependent plasticity (SRDP) [36]
We present a neuromorphic hardware system, which is comprised of multiple memristor arrays, Digital-Analog Converters (DACs), Analog-Digital Converters (ADCs) and many other assemblies, and is equipped with inference and training functions
Summary
The human brain is a highly efficient system, which consists of approximately 1011 neurons and 1015 synapses with merely 20 W power consumption [1–3]. The memristor with high density, low power consumption and tunable conductance has shown great promise for the synapses [14–17]. Another attribution to the inefficiency is that the recognition tasks are realized via supervised learning, which demands a large amount of training data and additional feedback circuits, leading to time latency and energy consumption [18–21], especially when online training is required [22–24]. Going beyond the device demonstrations, several hardware implementations of pattern learning by SRDP have been proposed [26,28]. A 196 × 10 SRDP neural network is constructed to demonstrate the online unsupervised learning of 10 MNIST digits, and about 90% classification accuracy is achieved
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
