2022/07/09 by João Batista P. Matos, Iury Bessa, Matos, João Batista P. +7 · 1 citation
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Software Engineering (cs.SE)
paper · pdf · doi:10.48550/arxiv.2207.04231
openalex publication_date 2022/07/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Neural networks are essential components of learning-based software systems. However, their high compute, memory, and power requirements make using them in low resources domains challenging. For this reason, neural networks are often quantized before deployment. Existing quantization techniques tend to degrade the network accuracy. We propose Counter-Example Guided Neural Network Quantization Refinement (CEG4N). This technique combines search-based quantization and equivalence verification: the former minimizes the computational requirements, while the latter guarantees that the network's output does not change after quantization. We evaluate CEG4N~on a diverse set of benchmarks, including large and small networks. Our technique successfully quantizes the networks in our evaluation while producing models with up to 72% better accuracy than state-of-the-art techniques.