We present new ideas which attempt to explain why Deep Learning works, taking lessons from Theoretical Chemistry, and integrating ideas from Protein Folding, Renormalization Group, and Quantum Chemistry. We address the i

First Page		Document Content
Date: 2016-06-23 15:50:48 Physics Theoretical physics Mathematical physics Quantum field theory Renormalization group Academia Statistical mechanics Protein structure Renormalization Deep learning Protein folding Energy landscape		We present new ideas which attempt to explain why Deep Learning works, taking lessons from Theoretical Chemistry, and integrating ideas from Protein Folding, Renormalization Group, and Quantum Chemistry. We address the i Add to Reading List Source URL: mmds-data.org Download Document from Source Website File Size: 12,22 KB Share Document on Facebook

	SYSTEMS OF POINTS WITH COULOMB INTERACTIONS SYLVIA SERFATY Abstract. Large ensembles of points with Coulomb interactions arise in various settings of condensed matter physics, classical and quantum mechanics, statistical DocID: 1xVYR - View Document
	Chaos, Complexity, and Statistical MechanicsChaos, Complexity, and Statistical Mechanics DocID: 1xVS6 - View Document
	Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology 1678 Probing Magnetism at the Atomic Scale: Non-Equilibrium Statistical Mechanics Theoretical Treatise DocID: 1v6vu - View Document
	Quantum Fields at Finite T and µ V. L. Yudichev Quantum Statistical Mechanics DocID: 1uKO8 - View Document
	Physica D–217 Defect turbulence and generalized statistical mechanics Karen E. Daniels a,1 , Christian Beck b , Eberhard Bodenschatz a,∗ a DocID: 1ujOo - View Document