Scientific intuition inspired by machine learning generated hypotheses

Abstract

Machine learning with application to questions in the physical sciences has become a widely used tool, successfully applied to classification, regression and optimization tasks in many areas. Research focus mostly lies in improving the accuracy of the machine learning models in numerical predictions, while scientific understanding is still almost exclusively generated by human researchers analysing numerical results and drawing conclusions. In this work, we shift the focus on the insights and the knowledge obtained by the machine learning models themselves. In particular, we study how it can be extracted and used to inspire human scientists to increase their intuitions and understanding of natural systems. We apply gradient boosting in decision trees to extract human interpretable insights from big data sets from chemistry and physics. In chemistry, we not only rediscover widely know rules of thumb but also find new interesting motifs that tell us how to control solubility and energy levels of organic molecules. At the same time, in quantum physics, we gain new understanding on experiments for quantum entanglement. The ability to go beyond numerics and to enter the realm of scientific insight and hypothesis generation opens the door to use machine learning to accelerate the discovery of conceptual understanding in some of the most challenging domains of science.

References in corpus (24)

• Machine learning and the physical sciences
• Machine learning phases of matter
• Deep learning for universal linear embeddings of nonlinear dynamics
• Multi-photon entanglement and interferometry
• Explainable Machine Learning for Scientific Insights and Discoveries
• Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Advances in High Dimensional Quantum Entanglement
• Deep neural network solution of the electronic Schrödinger equation
• Discovering physical concepts with neural networks
• Multi-photon entanglement in high dimensions
• Entanglement Certification $-$ From Theory to Experiment
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Automated Search for new Quantum Experiments
• The structure of multidimensional entanglement in multipartite systems
• Experimental GHZ Entanglement beyond Qubits
• Machine learning for long-distance quantum communication
• The entropy vector formalism and the structure of multidimensional entanglement in multipartite systems
• Computer-inspired Quantum Experiments
• Discovering Symmetry Invariants and Conserved Quantities by Interpreting Siamese Neural Networks
• Layered Quantum Key Distribution
• A search algorithm for quantum state engineering and metrology
• Experimental creation of Multi-Photon High-Dimensional Layered Quantum States
• Mermin inequalities for perfect correlations in many-qutrit systems

Cited by in corpus (3)

• On scientific understanding with artificial intelligence
• A Triumvirate of AI Driven Theoretical Discovery
• MEGAN: Multi-Explanation Graph Attention Network