# Cooperative Neural Network with Denoising Autoencoder

The study proposes CoNN-AL, which adds stream-based active learning to the Cooperative Neural Network with Denoising Autoencoder (CoNN-DAE) and uses Monte Carlo dropout uncertainty to decide in real time which incoming candidates are worth labeling for data-efficient partial inverse design; on a real-world automotive glass run channel dataset of more than 900,000 unique simulated designs, only 20,000 actively selected labels (about 2.3% of the training pool) yield R-squared of 0.967 to 0.982 across all missing-variable levels, approaching upper-bound models trained on far more data, and at harder levels it reaches R-squared of at least 0.95 with 30 to 40% fewer labels than random sampling.

The study proposes CoNN-AL, which adds stream-based active learning to the Cooperative Neural Network with Denoising Autoencoder (CoNN-DAE) and uses Monte Carlo dropout uncertainty to decide in real time which incoming candidates are worth labeling for data-efficient partial inverse design; on a real-world automotive glass run channel dataset of more than 900,000 unique simulated designs, only 20,000 actively selected labels (about 2.3% of the training pool) yield R-squared of 0.967 to 0.982 across all missing-variable levels, approaching upper-bound models trained on far more data, and at harder levels it reaches R-squared of at least 0.95 with 30 to 40% fewer labels than random sampling.