Education1990 Ph.D., Harvard University
ResearchTheory, computational, electronic structure theory, machine learning, materials theory, photophysics, spectroscopy
MACHINE LEARNING FOR CHEMISTRY
Molecules are composed of functional groups that behave similarly in different contexts. We are using machine learning to develop quantum chemical methods that take better advantage of this molecular similarity. In particular, we are developing neural networks that use quantum chemistry as an integral part of their prediction process. By training the neural network on data from ab initio computations, the neural net learns to predict molecular properties at a cost that is a small fraction of that of ab initio theory. We are also developing ways to use machine learning to control experimental conditions and drive reactions to desired outcomes.
Computational Modeling of Organic Semiconductors
We use electronic structure theory to probe the structure property relationships of conjugated polymers. This often involves extracting information on the structure and electronic properties of these materials from spectroscopy and other measurements. In our most recent work, we have been exploring how incorporation of heteroatoms into the conjugated backbone influences their properties, and how these properties may be modified by varying the sequence of the polymer units.
A Density Functional Tight Binding Layer for Deep Learning of Chemical Hamiltonians
Haichen Li, Christopher R. Collins, Matteus Tanha, Geoffrey J. Gordon, and David J. Yaron, Journal of chemical theory and computation (2018) http://dx.doi.org/10.1021/acs.jctc.8b00873
Tuning the Molecular Weight Distribution from Atom Transfer Radical Polymerization Using Deep Reinforcement Learning
Haichen Li, Christopher R. Collins, Thomas G. Ribelli, Krystof Matyjaszewski, Geoffrey J. Gordon, Tomasz Kowalewski, and David J. Yaron, Mol Syst Des Eng. 3, 496-508 (2018) https://doi.org/10.1039/C7ME00131B
Constant size descriptors for accurate machine learning models of molecular properties
Christopher R. Collins, Geoffrey J. Gordon, O. Anotole von Lilienfeld, and David J. Yaron, J. Chem. Phys. 148, 241718 (2018); https://doi.org/10.1063/1.5020441
In-Situ Platinum Deposition on Nitrogen-Doped Carbon Films as a Source of Catalytic Activity in a Hydrogen Evolution Reaction
Eric Gottlieb, Maciej Kopeć, Manali Banerjee, Jacob Mohin, David Yaron, Krzysztof Matyjaszewski, and Tomasz Kowalewski, ACS Appl. Mater. Interfaces, 8 (33), pp 21531–21538 (2016).
Conjugated polymers with repeated sequences of group 16 heterocycles synthesized through catalyst-transfer polycondensation
Chia-Hua Tsai, Andria Fortney, Yunyan Qiu, Roberto R. Gil, David Yaron, Tomasz Kowalewski, and Kevin J. T. Noonan, J. Am. Chem. Soc., 2016, 138 (21), pp 6798– 6804 (2016).
A Least-Squares Commutator in the Iterative Subspace Method for Accelerating Self-Consistent Field Convergence
Haichen Li and David J. Yaron, J. Chem. Theory Comput., 12 (11), pp 5322–5332 (2016).
The Efficiency of Worked Examples Compared to Erroneous Examples, “Tutored Problem Solving, and Problem Solving in Computer-Based Learning Environments.”
McLaren, Bruce M., Tamara van Gog, Craig Ganoe, Michael Karabinos, and David Yaron. Computers in Human Behavior 55, Part A (February): 87–99. (2016).
Imitation Learning for Accelerating Iterative Computation of Fixed Points in Quantum Chemistry
Tanha, Matteus, Tse-Han Huang, Geoffrey J. Gordon, and David Yaron, Paper presented at the 12th European Workshop on Reinforcement Learning (EWRL 2015), Lille, France, July (2015).
Spectral Fine Tuning of Cyanine Dyes: Electron Donor-Acceptor Substituted Analogues of Thiazole Orange
Rastede, Elizabeth E., Matteus Tanha, David Yaron, Simon C. Watkins, Alan S. Waggoner, and Bruce A. Armitage, Photochemical & Photobiological Sciences: Official Journal of the European Photochemistry Association and the European Society for Photobiology 14 (9). The Royal Society of Chemistry: 1703–12 (2015).
Worked Examples are more Efficient for Learning than High-Assistance Instructional Software
McLaren, Bruce M., Tamara van Gog, Craig Ganoe, David Yaron, and Michael Karabinos, International Journal of Artificial Intelligence in Education. Vol. 9112 Springer: 710-713 (2015).
Modeling Field-Induced Quenching in Poly(p-Phenylene Vinylene) Polymers and Oligomers
Legaspi, Christian M., Linda A. Peteanu, and David J. Yaron, The Journal of Physical Chemistry. B 119 (24) 7625–34 (2015).
Making Sense of Students’ Actions in an Open-Ended Virtual Laboratory Environment
Gal, Ya’akov, Oriel Uzan, Robert Belford, Michael Karabinos, and David Yaron, Journal of Chemical Education 92 (4). American Chemical Society: 610–16 (2015).
Developing Coarse-Grained Site Models for Excited Electronic States of Conjugated Polymers
Collins, Christopher R., and David J. Yaron, In Proceedings of SPIE 9549, Physical Chemistry of Interfaces and Nanomaterials XIV, edited by Sophia C. Hayes and Eric R. Bittner. Vol. 9549 (2015),
|2013–present||Professor, Carnegie Mellon University|
|1998–2013||Associate Professor, Carnegie Mellon University|
|1992–1998||Assistant Professor, Carnegie Mellon University|
|1990–1992||Postdoctoral Fellow, MIT|
Awards and Distinctions
|2017||Teaching Innovation Award, Carnegie Mellon University|
|2004||Award for Excellence: Post-secondary Educator
Carnegie Science Center Pittsburgh
|2003||Classics Award for Best Learning Object in Chemistry
Editor’s Choice for Exemplary Learning Object in any domain
Merlot Digital Library
|2001||Julius Ashkin Teaching Award
Mellon College of Science, Carnegie Mellon
|2000||Henry Dreyfus Teacher-Scholar Award
The Camile and Henry Dreyfus Foundation
Ecole Normale Superieure de Cachan, France