Synergies Between Quantum Mechanics and Machine Learning in Reaction Prediction

2016 ◽  
Vol 56 (11) ◽  
pp. 2125-2128 ◽  
Author(s):  
Peter Sadowski ◽  
David Fooshee ◽  
Niranjan Subrahmanya ◽  
Pierre Baldi
Keyword(s):  
Machine Learning ◽  
Quantum Mechanics ◽  
Reaction Prediction

scholarly journals Machine Learning: A Quantum Perspective

2021 ◽  
Author(s):  
Aishwarya Jhanwar ◽  
Manisha J. Nene
Keyword(s):  
Machine Learning ◽  
Quantum Mechanics ◽  
Quantum Computing ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Quantum Computers ◽  
Learning Tasks ◽  
Current Scenario ◽  
Chip Fabrication ◽  
Classical Computing

Recently, increased availability of the data has led to advances in the field of machine learning. Despite of the growth in the domain of machine learning, the proximity to the physical limits of chip fabrication in classical computing is motivating researchers to explore the properties of quantum computing. Since quantum computers leverages the properties of quantum mechanics, it carries the ability to surpass classical computers in machine learning tasks. The study in this paper contributes in enabling researchers to understand how quantum computers can bring a paradigm shift in the field of machine learning. This paper addresses the concepts of quantum computing which influences machine learning in a quantum world. It also states the speedup observed in different machine learning algorithms when executed on quantum computers. The paper towards the end advocates the use of quantum application software and throw light on the existing challenges faced by quantum computers in the current scenario.

Machine learning accelerates quantum mechanics predictions of molecular crystals

2021 ◽  
Author(s):  
Yanqiang Han ◽  
Imran Ali ◽  
Zhilong Wang ◽  
Junfei Cai ◽  
Sicheng Wu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Quantum Mechanics ◽  
Molecular Crystals

scholarly journals Artificial intelligence and thermodynamics help solving arson cases

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Sander Korver ◽  
Eva Schouten ◽  
Othonas A. Moultos ◽  
Peter Vergeer ◽  
Michiel M. P. Grutters ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Quantum Mechanics ◽  
Strong Indication ◽  
Initial Composition ◽  
Combine Machine ◽  
Error Bars ◽  
Main Components ◽  
Fire Scene ◽  
Important Evidence

AbstractIn arson cases, evidence such as DNA or fingerprints is often destroyed. One of the most important evidence modalities left is relating fire accelerants to a suspect. When gasoline is used as accelerant, the aim is to find a strong indication that a gasoline sample from a fire scene is related to a sample of a suspect. Gasoline samples from a fire scene are weathered, which prohibits a straightforward comparison. We combine machine learning, thermodynamic modeling, and quantum mechanics to predict the composition of unweathered gasoline samples starting from weathered ones. Our approach predicts the initial (unweathered) composition of the sixty main components in a weathered gasoline sample, with error bars of ca. 4% when weathered up to 80% w/w. This shows that machine learning is a valuable tool for predicting the initial composition of a weathered gasoline, and thereby relating samples to suspects.

scholarly journals Dataset Bias in the Natural Sciences: A Case Study in Chemical Reaction Prediction and Synthesis Design

2018 ◽  
Author(s):  
Ryan-Rhys Griffiths ◽  
Philippe Schwaller ◽  
Alpha Lee
Keyword(s):  
Machine Learning ◽  
Chemical Reaction ◽  
Design Problem ◽  
Data Fitting ◽  
Natural Sciences ◽  
Contextual Variables ◽  
Outlier Removal ◽  
Reaction Prediction ◽  
Synthesis Design

<div><div><div><div><div><div><p>Datasets in the Natural Sciences are often curated with the goal of aiding scientific understanding and hence may not always be in a form that facilitates the application of machine learning. In this paper, we identify three trends within the fields of chemical reaction prediction and synthesis design that require a change in direction. First, the manner in which reaction datasets are split into reactants and reagents encourages testing models in an unrealistically generous manner. Second, we highlight the prevalence of mislabelled data, and suggest that the focus should be on outlier removal rather than data fitting only. Lastly, we discuss the problem of reagent prediction, in addition to reactant prediction, in order to solve the full synthesis design problem, highlighting the mismatch between what machine learning solves and what a lab chemist would need. Our critiques are also relevant to the burgeoning field of using machine learning to accelerate progress in experimental Natural Sciences, where datasets are often split in a biased way, are highly noisy, and contextual variables that are not evident from the data strongly influence the outcome of experiments.</p></div></div></div></div></div></div>

Sign in / Sign up

Export Citation Format

Share Document