In literature, different approaches point to the use of different resistive memory (RRAM) device families such as PCM [1], OxRAM,CBRAM[2], and STTMRAM [3] for synaptic emulation in dedicated neuromorphic hardware. Most of theseworks justify the use ofRRAMdevices in hybrid learning hardware on grounds of their inherent advantages, such as ultra-high density, high endurance, high retention, CMOS compatibility, possibility of 3D integration, and lowpower consumption [4]. However, with the advent of more complex learning and weight update algorithms (beyond-STDP kinds), for example the ones inspired from Machine Learning, the peripheral synaptic circuit overhead considerably increases. Thus, use of RRAM cannot be justified on the merits of device properties alone. A more applicationoriented approach is needed to further strengthen the case of RRAM devices in such systems that exploit the device properties also for peripheral nonsynaptic and learning circuitry, beyond the usual synaptic application alone.In this chapter,we discuss two novel designs utilizing the inherent variability in resistive memory devices to successfully implement modified versions of Extreme Learning Machines and Restricted Boltzmann Machines in hardware.
CITATION STYLE
Parmar, V., & Suri, M. (2017). Exploiting variability in resistive memory devices for cognitive systems. In Cognitive Systems Monographs (Vol. 31, pp. 175–195). Springer Verlag. https://doi.org/10.1007/978-81-322-3703-7_9
Mendeley helps you to discover research relevant for your work.