Timezone: »

 
Poster
Deep Reasoning Networks for Unsupervised Pattern De-mixing with Constraint Reasoning
Di Chen · Yiwei Bai · Wenting Zhao · Sebastian Ament · John Gregoire · Carla Gomes

Tue Jul 14 07:00 AM -- 07:45 AM & Tue Jul 14 07:00 PM -- 07:45 PM (PDT) @ None #None

We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with constraint reasoning for solving pattern de-mixing problems, typically in an unsupervised or very-weakly-supervised setting. DRNets exploit problem structure and prior knowledge by tightly combining constraint reasoning with stochastic-gradient-based neural network optimization. Our motivating task is from materials discovery and concerns inferring crystal structures of materials from X-ray diffraction data (Crystal-Structure-Phase-Mapping). Given the complexity of its underlying scientific domain, we start by introducing DRNets on an analogous but much simpler task: de-mixing overlapping hand-written Sudokus (Multi-MNIST-Sudoku). On Multi-MNIST-Sudoku, DRNets almost perfectly recovered the mixed Sudokus' digits, with 100\% digit accuracy, outperforming the supervised state-of-the-art MNIST de-mixing models. On Crystal-Structure-Phase-Mapping, DRNets significantly outperform the state of the art and experts' capabilities, recovering more precise and physically meaningful crystal structures.

Author Information

Di Chen (Cornell University)
Yiwei Bai (Cornell University)
Wenting Zhao (Cornell University)
Sebastian Ament (Cornell University)
John Gregoire (Caltech)
Carla Gomes (Cornell University)

More from the Same Authors