Genetic Optimization of Training Sets for Improved Machine Learning Models of Molecular Properties
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
The interactions and structural formation of polyelectrolytes in solution and environmental stimuli-responsive water-soluble polymers are subjects of intense academic research, development, and application. An increasing number of novel materials are being ...
Discrete optimization is a difficult task common to many different areas in modern research. This type of optimization refers to problems where solution elements can assume one of several discrete values. The most basic form of discrete optimization is bin ...
Artificial immune systems (AIS) use the concepts and algorithms inspired by the theory of how the human immune system works. This document presents the design and initial evaluation of a new artificial immune system for collaborative spam filtering. Collab ...
The classical single-objective model calibration and validation approach using different time periods for each of them is known not to be sufficient to judge whether the model predictions are consistent or to detect model structural deficiencies. It is how ...
Good things come in small packages: For its moderate molecular weight, the metallostar complex [Fe{Gd2L(H2O)4}3]4− (see picture; L is a bipyridine–poly(aminocarboxylate) derivative) displays exceptionally high proton relaxivity, which is explained in terms ...
An analysis of unsupervised neural network models and the use of self-organizing maps in the real-time monitoring of power transformers was carried out. The application of genetic algorithms in a complex optimization problem, the allocation and parameters ...
We present an assessment of the performance of a new on-line bin packing algorithm, which can interpolate smoothly from the Next Fit to Best Fit algorithms, as well as encompassing a new class of heuristic which packs multiple blocks at once. The performan ...
Springer-Verlag New York, Ms Ingrid Cunningham, 175 Fifth Ave, New York, Ny 10010 Usa2001
An equation solver data reconciliation software has been used to build a validated model of a waste paper deinking mill, by combining control room measurements and process design specifications. An optimal sampling protocol to validate the model by using o ...
This paper describes an application of optimization and machine learning to load restoration in a generation-transmission system. An optimization procedure, combining a genetic algorithm and a power system dynamic simulator, generates the appropriate seque ...
Matching Pursuit is a greedy algorithmthat decomposes any signal into a linear expansion of waveforms taken from a redundant dictionary. Computing the projection of the signal on every element of the basis has a high computational cost. To reduce this comp ...
