Non-Neural Network Applications for Spiking Neuromorphic Hardware
Abstract: Increasing power costs for large-scale computing in a post-Moore’s Law system have forced the high-performance computing community to explore heterogeneous systems. Neuromorphic architectures, inspired by biological neural systems, have so far been relegated to auxiliary machine learning applications. Here, we discuss growing research showing the viability of ultra-low-power neural accelerators as co-processors for classic compute algorithms, such as random walk simulations and graph analytics.
Back to The 3rd International Workshop on Post-Moore Era Supercomputing (PMES) Archive Listing
Back to Full Workshop Archive Listing