Energy consumption analysis for various memristive networks under different learning strategies

• Estimation methodology for energy consumed by memristor is established.
• Energy comparisons for different learning strategies in various networks are touched.
• Less-pulses and low-power-first modulation methods are energy efficient.
• Proper decreasing the memristor modulation precision reduces the energy consumption.
• Helpful solutions for power improving in memristive systems are proposed.

Recently, various memristive systems emerge to emulate the efficient computing paradigm of the brain cortex; whereas, how to make them energy efficient still remains unclear, especially from an overall perspective. Here, a systematical and bottom-up energy consumption analysis is demonstrated, including the memristor device level and the network learning level. We propose an energy estimating methodology when modulating the memristive synapses, which is simulated in three typical neural networks with different synaptic structures and learning strategies for both offline and online learning. These results provide an in-depth insight to create energy efficient brain-inspired neuromorphic devices in the future.