Predicting thermoelectric properties from chemical formula with explicitly identifying dopant effects

Dopants play an important role in synthesizing materials to improve target materials properties or stabilize the materials. In particular, the dopants are essential to improve thermoelectic performances of the materials. However, existing machine learning methods cannot accurately predict the materials properties of doped materials due to severely nonlinear relations with their materials properties. Here, we propose a unified architecture of neural networks, called DopNet, to accurately predict the materials properties of the doped materials. DopNet identifies the effects of the dopants by explicitly and independently embedding the host materials and the dopants. In our evaluations, DopNet outperformed existing machine learning methods in predicting experimentally measured thermoelectric properties, and the error of DopNet in predicting a figure of merit (ZT) was 0.06 in mean absolute error. In particular, DopNet was significantly effective in an extrapolation problem that predicts ZTs of unknown materials, which is a key task to discover novel thermoelectric materials.

Application of Recent Developments in Deep Learning to ANN-based Automatic Berthing Systems

Previous studies on Artificial Neural Network (ANN)-based automatic berthing showed considerable increases in performance by training ANNs with a set of berthing datasets. However, the berthing performance deteriorated when an extrapolated initial position was given. To overcome the extrapolation problem and improve the training performance, recent developments in Deep Learning (DL) are adopted in this paper. Recent activation functions, weight initialization methods, input data-scaling methods, a higher number of hidden layers, and Batch Normalization (BN) are considered, and their effectiveness has been analyzed based on loss functions, berthing performance histories, and berthing trajectories. Finally, it is shown that the use of recent activation and weight initialization method results in faster training convergence and a higher number of hidden layers. This leads to a better berthing performance over the training dataset. It is found that application of the BN can overcome the extrapolated initial position problem.

The Measurement Problem of Consciousness

This paper addresses what we consider to be the most pressing challenge for the emerging science of consciousness: the measurement problem of consciousness. That is, by what methods can we determine the presence of and properties of consciousness? Most methods are currently developed through evaluation of the presence of consciousness in humans and here we argue that there are particular problems in application of these methods to nonhuman cases—what we call the indicator validity problem and the extrapolation problem. The first is a problem with the application of indicators developed using the differences between conscious and unconscious processing in humans to the identification of other conscious vs. nonconscious organisms or systems. The second is a problem in extrapolating any indicators developed in humans or other organisms to artificial systems. However, while pressing ethical concerns add urgency to the attribution of consciousness and its attendant moral status to nonhuman animals and intelligent machines, we cannot wait for certainty and we advocate the use of a precautionary principle to avoid causing unintentional harm. We also intend that the considerations and limitations discussed in this paper can be used to further analyze and refine the methods of consciousness science with the hope that one day we may be able to solve the measurement problem of consciousness.

Numerical Solution for the Extrapolation Problem of Analytic Functions

In this work, a numerical solution for the extrapolation problem of a discrete set of n values of an unknown analytic function is developed. The proposed method is based on a novel numerical scheme for the rapid calculation of higher order derivatives, exhibiting high accuracy, with error magnitude of O(10−100) or less. A variety of integrated radial basis functions are utilized for the solution, as well as variable precision arithmetic for the calculations. Multiple alterations in the function’s direction, with no curvature or periodicity information specified, are efficiently foreseen. Interestingly, the proposed procedure can be extended in multiple dimensions. The attained extrapolation spans are greater than two times the given domain length. The significance of the approximation errors is comprehensively analyzed and reported, for 5832 test cases.