Abstract
Hierarchical Temporal Memory (HTM) has been known as a software framework to model the brain’s neocortical operation. However, mimicking the brain’s neocortical operation by not software but hardware is more desirable, because the hardware can not only describe the neocortical operation, but can also employ the brain’s architectural advantages. To develop a hybrid circuit of memristor and Complementary Metal-Oxide-Semiconductor (CMOS) for realizing HTM’s spatial pooler (SP) by hardware, memristor defects such as stuck-at-faults and variations should be considered. For solving the defect problem, we first show that the boost-factor adjustment can make HTM’s SP defect-tolerant, because the false activation of defective columns are suppressed. Second, we propose a memristor-CMOS hybrid circuit with the boost-factor adjustment to realize this defect-tolerant SP by hardware. The proposed circuit does not rely on the conventional defect-aware mapping scheme, which cannot avoid the false activation of defective columns. For the Modified subset of National Institute of Standards and Technology (MNIST) vectors, the boost-factor adjusted crossbar with defects = 10% shows a rate loss of only ~0.6%, compared to the ideal crossbar with defects = 0%. On the contrary, the defect-aware mapping without the boost-factor adjustment demonstrates a significant rate loss of ~21.0%. The energy overhead of the boost-factor adjustment is only ~0.05% of the programming energy of memristor synapse crossbar.
Highlights
The human brain’s neocortex covers the brain’s surficial area, which is known to carry out the most intelligence functions
The proposed circuit does not rely on the conventional defect-aware mapping scheme, which cannot avoid the false activation of defective columns
To realize Hierarchical Temporal Memory (HTM)’s spatial pooler (SP) by hardware, in this paper, we developed the memristor-Complementary Metal-Oxide-Semiconductor (CMOS) hybrid circuit
Summary
The human brain’s neocortex covers the brain’s surficial area, which is known to carry out the most intelligence functions. The thickness of neocortex has been observed as thin as 2.5 mm, where six layers are stacked one-by-one [1,2,3]. The six neocortical layers seem to be columnar, in which the complicated vertical and horizontal synaptic connections are intertwined among neurons to form the. The neocortical neurons collectively respond to human’s sensory information from retina, cochlea, and olfactory organ [6]. The collective activation of neocortical neurons are trained over and over with respect to time, by changing the synaptic connection’s strength according to the sensory stimuli. The neuronal activation and synaptic plasticity can be thought of as a fundamental aspect of human perception and cognition, which are computed in a different way from the conventional Von Neumann machines
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.
