Learning molecular energies using localized graph kernels
نویسندگان
چکیده
منابع مشابه
Learning molecular energies using localized graph kernels.
Recent machine learning methods make it possible to model potential energy of atomic configurations with chemical-level accuracy (as calculated from ab initio calculations) and at speeds suitable for molecular dynamics simulation. Best performance is achieved when the known physical constraints are encoded in the machine learning models. For example, the atomic energy is invariant under global ...
متن کاملUnsupervised learning of graph languages using kernels
In most domains, machine learning involves discovering the relationship between objects. Such relationships are naturally represented as graphs. Up until now, most work on learning graphs consisted of extending well-known approaches from the field of machine learning to deal with more complex structures. For both technical and conceptual reasons, borrowing techniques from Grammar Induction (GI)...
متن کاملSurvey of Graph Energies
Let graph energy is a graph--spectrum--based quantity, introduced in the 1970s. After a latent period of 20--30 years, it became a popular topic of research both in mathematical chemistry and in ``pure'' spectral graph theory, resulting in over 600 published papers. Eventually, scores of different graph energies have been conceived. In this article we...
متن کاملLazy and Eager Relational Learning Using Graph-Kernels
Machine learning systems can be distinguished along two dimensions. The first is concerned with whether they deal with a feature based (propositional) or a relational representation; the second with the use of eager or lazy learning techniques. The advantage of relational learning is that it can capture structural information. We compare several machine learning techniques along these two dimen...
متن کاملLearning Models of Relational MDPs Using Graph Kernels
Relational reinforcement learning is the application of reinforcement learning to structured state descriptions. Model-based methods learn a policy based on a known model that comprises a description of the actions and their effects as well as the reward function. If the model is initially unknown, one might learn the model first and then apply the model-based method (indirect reinforcement lea...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Journal of Chemical Physics
سال: 2017
ISSN: 0021-9606,1089-7690
DOI: 10.1063/1.4978623