On-Chip Compensation of Device-Mismatch Effects in Analog VLSI Neural Networks
نویسندگان
چکیده
Device mismatch in VLSI degrades the accuracy of analog arithmetic circuits and lowers the learning performance of large-scale neural networks implemented in this technology. We show compact, low-power on-chip calibration techniques that compensate for device mismatch. Our techniques enable large-scale analog VLSI neural networks with learning performance on the order of 10 bits. We demonstrate our techniques on a 64-synapse linear perceptron learning with the Least-Mean-Squares (LMS) algorithm, and fabricated in a 0.35μm CMOS process.
منابع مشابه
Subspace-Based Face Recognition in Analog VLSI
We describe an analog-VLSI neural network for face recognition based on subspace methods. The system uses a dimensionality-reduction network whose coefficients can be either programmed or learned on-chip to perform PCA, or programmed to perform LDA. A second network with userprogrammed coefficients performs classification with Manhattan distances. The system uses on-chip compensation techniques...
متن کاملPrecise deep neural network computation on imprecise low-power analog hardware
There is an urgent need for compact, fast, and power-efficient hardware implementations of state-of-the-art artificial intelligence. Here we propose a power-efficient approach for real-time inference, in which deep neural networks (DNNs) are implemented through low-power analog circuits. Although analog implementations can be extremely compact, they have been largely supplanted by digital desig...
متن کاملA VLSI neuromorphic device for implementing spike-based neural networks
We present a neuromorphic VLSI device which comprises hybrid analog/digital circuits for implementing networks of spiking neurons. Each neuron integrates input currents from a row of multiple analog synaptic circuit. The synapses integrate incoming spikes, and produce output currents which have temporal dynamics analogous to those of biological post synaptic currents. The VLSI device can be use...
متن کاملEffects of Analog-VLSI Hardware on the Performance of the LMS Algorithm
Device mismatch, charge leakage and nonlinear transfer functions limit the resolution of analog-VLSI arithmetic circuits and degrade the performance of neural networks and adaptive filters built with this technology. We present an analysis of the impact of these issues on the convergence time and residual error of a linear perceptron using the Least-Mean-Square (LMS) algorithm. We also identify...
متن کاملWeight Perturbation: An Optimal Architecture and Learning Technique for Analog VLSI Feedforward and Recurrent Multilayer Networks
Previous work on analog VLSI implementation of multilayer perceptrons with on-chip learning has mainly targeted the implementation of algorithms such as back-propagation. Although back-propagation is efficient, its implementation in analog VLSI requires excessive computational hardware. It is shown that using gradient descent with direct approximation of the gradient instead of back-propagation...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2004