Optimal training of a structured ensemble of Binarized Neural Networks with Mixed-Integer Linear Programming techniques
Simone Milanesi, Ambrogio Maria Bernardelli PhD students at the CompOpt Lab (University of Pavia) Binarized Neural Networks (BNNs) are receiving increasing attention due to their lightweight architecture and ability to run on low-power devices.The Mixed-Integer Linear Programming (MILP) approach achieves the state of the art for training classification BNNs when limited data are available.We propose […]