Search

Built upon the decision tree (DT) classification and regression idea, the subspace learning machine (SLM) has been recently proposed to offer higher performance in general classification and regression tasks. Its performance improvement is reached at the expense of higher computational complexity. In this work, we investigate two ways to accelerate SLM. First, we adopt the particle swarm optimization (PSO) algorithm to speed up the search of a discriminant dimension that is expressed as a linear combination of current dimensions. The search of optimal weights in the linear combination is computationally heavy. It is accomplished by probabilistic search in original SLM. The acceleration of SLM by PSO requires 10-20 times fewer iterations. Second, we leverage parallel processing in the SLM implementation. Experimental results show that the accelerated SLM method achieves a speed up factor of 577 in training time while maintaining comparable classification/regression performance of original SLM.

Nitride has been drawing much attention due to its wide range of applications in optoelectronics and remains plenty of room for materials design and discovery. Here, a large set of nitrides have been designed, with their band gap and alignment being studied by first-principles calculations combined with machine learning. Band gap and band offset against wurtzite GaN accurately calculated by the combination of screened hybrid functional of HSE and DFT-PBE were used to train and test machine learning models. After comparison among different techniques of machine learning, when elemental properties are taken as features, support vector regression (SVR) with radial kernel performs best for predicting both band gap and band offset with prediction root mean square error (RMSE) of 0.298 eV and 0.183 eV, respectively. The former is within HSE calculation uncertainty and the latter is small enough to provide reliable predictions. Additionally, when band gap calculated by DFT-PBE was added into the feature space, band gap prediction RMSE decreases to 0.099 eV. Through a feature engineering algorithm, elemental feature space based band gap prediction RMSE further drops by around 0.005 eV and the relative importance of elemental properties for band gap prediction was revealed. Finally, band gap and band offset of all designed nitrides were predicted and two trends were noticed that as the number of cation types increases, band gap tends to narrow down while band offset tends to go up. The predicted results will be a useful guidance for precise investigation on nitride engineering., Comment: Contact: Yang Huang, yah048@ucsd.edu

We propose and fabricate a dual-emitter light-induced neuromorphic device composed of two light-induced devices with a common collector and base. Two InGaN multiple quantum well diodes (MQW-diodes) are used as the emitters to generate light, and one InGaN MQW-diode is used as the common collector to absorb the emitted light. When the presynaptic voltages are synchronously applied to the two emitters, the collector demonstrates an adding together of the excitatory post synaptic voltage (EPSV). The width and period of the two input signals constitute the code to generate spatial summation and recognition effects at the same time. Experimental results confirm that temporal summation caused by the repetitive-pulse facilitation could significantly strengthen the spatial summation effect due to the adding together behavior when the repetitive stimulations are applied to the two emitters in rapid succession. Particularly, the resonant summation effect occurs at the co-summation region when the two repetitive-pulse signals have a resonant period, which offers a more sophisticated spatiotemporal EPSV summation function for the dual-emitter neuromorphic device.