Neural Network Verification as Piecewise Linear Optimization
Institute for Pure & Applied Mathematics (IPAM) via YouTube
Overview
Syllabus
Intro
Neural network verification
Key insights and approach
Optimization over a trained neural network
Fitting unknown functions to make predictions
Application: Deep reinforcement learning
Application: Designing DNA for protein binding
Neural networks in one slide
Most important theoretical result
MIP formulations for a single ReLU neuron
MIP formulation strength
Formulations for convex PWL functions
Network 1: Small network standard training
Propagation algorithms
Computational results
Extensions: Binarized and quantized networks
Taught by
Institute for Pure & Applied Mathematics (IPAM)