Precise neural network computation with imprecise analog devices
This addresses the challenge of using imprecise analog devices for efficient neural network computation, enabling reduced circuit complexity and power consumption, particularly for future nanodevices with high variability.
The paper tackles the problem of device mismatch in analog neural network circuits by proposing a deep learning framework that compensates for variations during training, eliminating the need for mismatch minimization. Results from simulations and a prototype chip show processing efficiency comparable to state-of-the-art digital implementations.
The operations used for neural network computation map favorably onto simple analog circuits, which outshine their digital counterparts in terms of compactness and efficiency. Nevertheless, such implementations have been largely supplanted by digital designs, partly because of device mismatch effects due to material and fabrication imperfections. We propose a framework that exploits the power of deep learning to compensate for this mismatch by incorporating the measured device variations as constraints in the neural network training process. This eliminates the need for mismatch minimization strategies and allows circuit complexity and power-consumption to be reduced to a minimum. Our results, based on large-scale simulations as well as a prototype VLSI chip implementation indicate a processing efficiency comparable to current state-of-art digital implementations. This method is suitable for future technology based on nanodevices with large variability, such as memristive arrays.