DeepAI AI Chat
Log In Sign Up

Robustness of Neural Networks to Parameter Quantization

by   Abhishek Murthy, et al.
Texas Tech University

Quantization, a commonly used technique to reduce the memory footprint of a neural network for edge computing, entails reducing the precision of the floating-point representation used for the parameters of the network. The impact of such rounding-off errors on the overall performance of the neural network is estimated using testing, which is not exhaustive and thus cannot be used to guarantee the safety of the model. We present a framework based on Satisfiability Modulo Theory (SMT) solvers to quantify the robustness of neural networks to parameter perturbation. To this end, we introduce notions of local and global robustness that capture the deviation in the confidence of class assignments due to parameter quantization. The robustness notions are then cast as instances of SMT problems and solved automatically using solvers, such as dReal. We demonstrate our framework on two simple Multi-Layer Perceptrons (MLP) that perform binary classification on a two-dimensional input. In addition to quantifying the robustness, we also show that Rectified Linear Unit activation results in higher robustness than linear activations for our MLPs.


page 1

page 2

page 3

page 4


QNNVerifier: A Tool for Verifying Neural Networks using SMT-Based Model Checking

QNNVerifier is the first open-source tool for verifying implementations ...

ILMPQ : An Intra-Layer Multi-Precision Deep Neural Network Quantization framework for FPGA

This work targets the commonly used FPGA (field-programmable gate array)...

Edge Inference with Fully Differentiable Quantized Mixed Precision Neural Networks

The large computing and memory cost of deep neural networks (DNNs) often...

Verifying Low-dimensional Input Neural Networks via Input Quantization

Deep neural networks are an attractive tool for compressing the control ...

QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks

Deep learning has become a promising programming paradigm in software de...

Analysis of Quantization on MLP-based Vision Models

Quantization is wildly taken as a model compression technique, which obt...

Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks

We present an approach for the verification of feed-forward neural netwo...