Formally Verifying Analog Neural Networks Under Process Variations Using Polynomial Zonotopes
For designers of analog neural networks, this work provides a fast formal verification method to ensure reliability under manufacturing variations, replacing slow Monte Carlo simulations.
The paper presents a polynomial-based model for analog neural networks under process variations and uses reachability analysis with polynomial zonotopes to formally verify circuit behavior, reducing verification time from days to seconds while enclosing 99% of variation samples.
Analog neural networks are gaining attention due to their efficiency in terms of power consumption and processing speed. However, since analog neural networks are implemented as physical circuits, they are highly sensitive to manufacturing process variations, which can cause large deviations from the nominal model. We present a polynomial-based model that resembles the performance of the neuron circuit under process variations. Then, we formally verify the behavior of the circuit-level model using reachability analysis with polynomial zonotopes, thus, avoiding conventional, time-consuming Monte Carlo simulations. We evaluate our proposed verification approach on three different datasets, verifying both fully-connected and convolutional analog neural networks. Our experimental results confirm the effectiveness of our verification approach by reducing the verification time from days to seconds while enclosing 99% of the variation samples.