Simplifying Neural Networks with the Marabou Verification Engine

by   Sumathi Gokulanathan, et al.

Deep neural network (DNN) verification is an emerging field, with diverse verification engines quickly becoming available. Demonstrating the effectiveness of these tools on real-world DNNs is an important step towards their wider adoption. We focus here on the recently proposed Marabou verification tool, and demonstrate its usage for a novel application: simplifying neural networks, by reducing the size of a DNN without harming its accuracy. We report on the work-flow of the simplification process, and on its potential significance and applicability to domains of interest.



page 1

page 2

page 3

page 4


Refactoring Neural Networks for Verification

Deep neural networks (DNN) are growing in capability and applicability. ...

Neural Network Verification with Proof Production

Deep neural networks (DNNs) are increasingly being employed in safety-cr...

DeepSaucer: Unified Environment for Verifying Deep Neural Networks

In recent years, a number of methods for verifying DNNs have been develo...

Neural Network Robustness Verification on GPUs

Certifying the robustness of neural networks against adversarial attacks...

DNNV: A Framework for Deep Neural Network Verification

Despite the large number of sophisticated deep neural network (DNN) veri...

Artificial Intelligence and Location Verification in Vehicular Networks

Location information claimed by devices will play an ever-increasing rol...

Parametric Chordal Sparsity for SDP-based Neural Network Verification

Many future technologies rely on neural networks, but verifying the corr...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.