Performance and Comparisons of STDP based and Non-STDP based Memristive Neural Networks on Hardware
This work addresses hardware realization challenges for memristive neural networks, offering a more efficient alternative for engineering applications, though it is incremental as it builds on existing MNN frameworks.
The paper tackles the hardware inefficiency of STDP-based memristive neural networks by constructing a non-STDP unsupervised MNN, showing it matches STDP in accuracy and convergence for pattern recognition while using fewer hardware resources and achieving higher processing speed.
With the development of research on memristor, memristive neural networks (MNNs) have become a hot research topic recently. Because memristor can mimic the spike timing-dependent plasticity (STDP), the research on STDP based MNNs is rapidly increasing. However, although state-of-the-art works on STDP based MNNs have many applications such as pattern recognition, STDP mechanism brings relatively complex hardware framework and low processing speed, which block MNNs' hardware realization. A non-STDP based unsupervised MNN is constructed in this paper. Through the comparison with STDP method on the basis of two common structures including feedforward and crossbar, non-STDP based MNNs not only remain the same advantages as STDP based MNNs including high accuracy and convergence speed in pattern recognition, but also better hardware performance as few hardware resources and higher processing speed. By virtue of the combination of memristive character and simple mechanism, non-STDP based MNNs have better hardware compatibility, which may give a new viewpoint for memristive neural networks' engineering applications.