A Novel Method for Inference of Chemical Compounds of Cycle Index Two with Desired Properties Based on Artificial Neural Networks and Integer Programming

Inference of chemical compounds with desired properties is important for drug design, chemo-informatics, and bioinformatics, to which various algorithmic and machine learning techniques have been applied. Recently, a novel method has been proposed for this inference problem using both artificial neural networks (ANN) and mixed integer linear programming (MILP). This method consists of the training phase and the inverse prediction phase. In the training phase, an ANN is trained so that the output of the ANN takes a value nearly equal to a given chemical property for each sample. In the inverse prediction phase, a chemical structure is inferred using MILP and enumeration so that the structure can have a desired output value for the trained ANN. However, the framework has been applied only to the case of acyclic and monocyclic chemical compounds so far. In this paper, we significantly extend the framework and present a new method for the inference problem for rank-2 chemical compounds (chemical graphs with cycle index 2). The results of computational experiments using such chemical properties as octanol/water partition coefficient, melting point, and boiling point suggest that the proposed method is much more useful than the previous method.

Optional Stopping in a Heteroscedastic World

When making decisions, animals must trade off the benefits of information harvesting against the opportunity cost of prolonged deliberation. Deciding when to stop accumulating information and commit to a choice is challenging in natural environments, where the reliability of decision-relevant information may itself vary unpredictably over time (variable variance or “heteroscedasticity”). We asked humans to perform a categorisation task in which discrete, continuously-valued samples (oriented gratings) arrived in series until the observer made a choice. Human behaviour was best described by a model that adaptively weighted sensory signals by their inverse prediction error, and integrated the resulting quantities to a collapsing decision threshold. This model approximated the output of a Bayesian model that computed the full posterior probability of a correct response, and successfully predicted adaptive weighting of decision information in neural signals. Adaptive weighting of decision information may have evolved to promote optional stopping in hetereoscedastic natural environments.

Heuristic Approach to Multivariate Inverse Prediction Problem using Data Reconciliation

Some engineering waste management tasks require a complete data sets of its production. However, these sets are not available in most cases. Whether they are not archiving at all or are unavailable for their sensitivity. This article deals with the issue of incomplete datasets at the microregional level. For estimates, the data from higher territorial units and additional information from the micro-region are used. The techniques used in this estimation are illustrated by an example in the field of waste management. In particular, it is an estimate of the amount of waste in individual municipalities. It is based on recorded waste production at district level and total waste management costs, which is available at a municipal level. To estimate the waste production, combinations of linear regression models with random forest models were used, followed by correction by quadratic and nonlinear optimization models. Such task could be seen as a multivariate version of inverse prediction (or calibration) problem, which is not solvable analytically. To test this approach, data for 2010 - 2015 measured in the Czech Republic were used.