Search

This article proposes a multi-label classification algorithm capable of continual learning by applying an Adaptive Resonance Theory (ART)-based clustering algorithm and the Bayesian approach for label probability computation. The ART-based clustering algorithm adaptively and continually generates prototype nodes corresponding to given data, and the generated nodes are used as classifiers. The label probability computation independently counts the number of label appearances for each class and calculates the Bayesian probabilities. Thus, the label probability computation can cope with an increase in the number of labels. Experimental results with synthetic and real-world multi-label datasets show that the proposed algorithm has competitive classification performance to other well-known algorithms while realizing continual learning.

Oxygen evolution reaction (OER) catalysts play an essential role in energy-conversion electrochemical reactions. High-entropy oxides (HEOs) were recently investigated as promising candidates to realize highly active and cost-effective OER catalysts. Since the vast composition space for the HEOs needs considerable efforts to find promising catalysts, the further development beyond simple chemical compositions like equimolar ones has not been achieved yet. In this study, we conducted the fast and efficient design of the perovskite of La(Cr, Mn, Fe, Co, Ni)O3with high OER catalytic activity using Bayesian optimization and found the relationship between chemical compositions and OER catalytic activities. The multielement perovskites with the optimized compositions exhibited much higher activities than the equimolar LaCr1/5Mn1/5Fe1/5Co1/5Ni1/5O3, which was previously reported as an active catalyst. Bayesian optimization adjusted the concentrations of OER active elements of Fe, Co, and Ni in high contents to enhance the catalytic activities. The optimization also indicates that the OER inactive elements (Cr and Mn) in perovskites even promote the OER activities. These findings suggest the solution of data-based predictions to improve catalytic performances in multielement transition-metal oxides.

Quantum-inspired computing is an emerging research area, which has significantly improved the capabilities of conventional algorithms. In general, quantum-inspired hopfield associative memory (QHAM) has demonstrated quantum information processing in neural structures. This has resulted in an exponential increase in storage capacity while explaining the extensive memory, and it has the potential to illustrate the dynamics of neurons in the human brain when viewed from quantum mechanics perspective although the application of QHAM is limited as an autoassociation. We introduce a quantum-inspired multidirectional associative memory (QMAM) with a one-shot learning model, and QMAM with a self-convergent iterative learning model (IQMAM) based on QHAM in this paper. The self-convergent iterative learning enables the network to progressively develop a resonance state, from inputs to outputs. The simulation experiments demonstrate the advantages of QMAM and IQMAM, especially the stability to recall reliability.