Improving Classification Performance in Dendritic Neuron Models through Practical Initialization Strategies.

A dendritic neuron model (DNM) is a deep neural network model with a unique dendritic tree structure and activation function. Effective initialization of its model parameters is crucial for its learning performance. This work proposes a novel initialization method specifically designed to improve the performance of DNM in classifying high-dimensional data, notable for its simplicity, speed, and straightforward implementation. Extensive experiments on benchmark datasets show that the proposed method outperforms traditional and recent initialization methods, particularly in datasets consisting of high-dimensional data. In addition, valuable insights into the behavior of DNM during training and the impact of initialization on its learning performance are provided. This research contributes to the understanding of the initialization problem in deep learning and provides insights into the development of more effective initialization methods for other types of neural network models. The proposed initialization method can serve as a reference for future research on initialization techniques in deep learning.

Interpretability Diversity for Decision-Tree-Initialized Dendritic Neuron Model Ensemble.

To construct a strong classifier ensemble, base classifiers should be accurate and diverse. However, there is no uniform standard for the definition and measurement of diversity. This work proposes a learners' interpretability diversity (LID) to measure the diversity of interpretable machine learners. It then proposes a LID-based classifier ensemble. Such an ensemble concept is novel because: 1) interpretability is used as an important basis for diversity measurement and 2) before its training, the difference between two interpretable base learners can be measured. To verify the proposed method's effectiveness, we choose a decision-tree-initialized dendritic neuron model (DDNM) as a base learner for ensemble design. We apply it to seven benchmark datasets. The results show that the DDNM ensemble combined with LID obtains superior performance in terms of accuracy and computational efficiency compared to some popular classifier ensembles. A random-forest-initialized dendritic neuron model (RDNM) combined with LID is an outstanding representative of the DDNM ensemble.

Enhanced Ageing Performance of Sulfonic Acid-Grafted Pt/C Catalysts.

Chemical functionalization of carbon support for Pt catalysts is a promising way to enhance the performance of catalysts. In this study, Pt/C catalysts grafted with various amounts of phenylsulfonic acid groups were prepared under mild conditions. The influence of sulfonic acid groups on the physiochemical characteristics and electrochemical activities of the modified catalysts were studied using X-ray diffraction, X-ray photoelectron spectroscopy, a transmission electron microscope, and cyclic voltammetry (CV). The presence of the chemical groups enhanced the hydrogen adsorption onto/desorption off the Pt surface during the CV cycling. In contrast, the hydrogen peaks of the grafted catalysts increased after 500 CV cycles, especially for Pt (111) facets. The highest electrochemical surface area (ECSA) after the aging test was obtained for the catalyst with 18.0 wt.% graft, which was ca. 87.3% higher than that of the non-functionalized Pt catalyst. In the density functional theory (DFT) calculation, it was proven that SO3H adsorption on the crystalline was beneficial for Pt stability. The adsorption energy and bond distance of the adsorbed SO3H on Pt (110), (100), and (111) surfaces were calculated. All the stable configurations were obtained when O from S-O single bond or S was bound to the Pt surface, with the adsorption energy following the trend of (111)F > (100)H > (110)H. This result was consistent with the ECSA experiment, which explained the high electrochemical stability of the sulfonic acid groups-grafted Pt/C catalyst.

Decision-Tree-Initialized Dendritic Neuron Model for Fast and Accurate Data Classification.

This work proposes a decision tree (DT)-based method for initializing a dendritic neuron model (DNM). Neural networks become larger and larger, thus consuming more and more computing resources. This calls for a strong need to prune neurons that do not contribute much to their network's output. Pruning those with low contribution may lead to a loss of accuracy of DNM. Our proposed method is novel because 1) it can reduce the number of dendrites in DNM while improving training efficiency without affecting accuracy and 2) it can select proper initialization weight and threshold of neurons. The Adam algorithm is used to train DNM after its initialization with our proposed DT-based method. To verify its effectiveness, we apply it to seven benchmark datasets. The results show that decision-tree-initialized DNM is significantly better than the original DNM, k-nearest neighbor, support vector machine, back-propagation neural network, and DT classification methods. It exhibits the lowest model complexity and highest training speed without losing any accuracy. The interactions among attributes can also be observed in its dendritic neurons.