machine-learning algorithmsadsorption energyon-lattice modelsoff-lattice modelscluster expansionsneural networkAdsorption energies on the surface sites of heterogeneous catalysts,together with the Sabatier volc
The techniques ranges from heuristically derived hand-crafted feature-based traditional machine learning algorithms to the recently de-veloped hierarchically self-evolving feature-based deep learn-ing algorithms. AR continues to remain a challenging prob-lem in uncontrolled smart environments despite the ...
This new volume provides a collection of chapters on diverse topics in machine learning algorithms and security analytics, AI and machine learning, and network security applications. It presents a variety of design algorithms that allow computers to employ machine learning to display behavior learned fr...
In recent years, the availability of large datasets combined with the improvement in algorithms and the exponential growth in computing power led to an unparalleled surge of interest in the topic of machine learning. Nowadays, machine learning algorithms are successfully employed for classification, regr...
For interventional and counterfactual analysis, data-driven approaches need to produce reliable estimates for the parameters that govern the relationship between input and output variables. Machine learning algorithms are typically not built for this purpose. Historically, the machine learning community has ...
In principle, the development of soft sensors can be regarded as a regression problem, so various supervised machine learning algorithms have been applied, as is comprehensively documented in Ref. [30]. The promise of utilizing representation learning in building soft sensors was first pointed out ...
Finally, machine learning algorithms may also lead to strategies for making the so-called “inverse design” of materials possible. Inverse design refers to the paradigm whereby one seeks to identify materials that satisfy a target set of desired properties (in this parlance, the “forward” proces...
Finally, machine learning algorithms may also lead to strategies for making the so-called “inverse design” of materials possible. Inverse design refers to the paradigm whereby one seeks to identify materials that satisfy a target set of desired properties (in this parlance, the “forward” proces...
Robust machine learning typically refers to the robustness of machine learning algorithms. For a machine learning algorithm to be considered robust, either the testing error has to be consistent with the training error, or the performance is stable after adding some noise to the dataset. This repo...
Deng and Yu84 defined the concept of deep learning as a class of machine learning algorithms that: Bengio et al15 introduced the stacked autoencoders and confirmed the hypothesis that the greedy layer-wise unsupervised training strategy mostly helps the optimization, by initializing weights in a ...