Search Results (3)

This study presents a gradient-informed proxy initialization framework designed to improve training efficiency and predictive performance in deep learning models for time-series forecasting. The method extends the Laor Initialization approach by introducing backward gradient norm clustering as a selection criterion for input-layer weights, evaluated through a lightweight, architecture-agnostic proxy model. Only the numerical input layer adopts the selected initialization, while internal components retain standard schemes such as Xavier, Kaiming, or Orthogonal, maintaining compatibility and reducing overhead. The framework is evaluated on a real-world financial forecasting task: identifying high-risk equities from the Thai Market Surveillance Measure List, a domain characterized by label imbalance, non-stationarity, and limited data volume. Experiments across five architectures, including Transformer, ConvTran, and MMAGRU-FCN, show that the proposed strategy improves convergence speed and classification accuracy, particularly in deeper and hybrid models. Results in recurrent-based models are competitive but less pronounced. These findings support the method’s practical utility and generalizability for forecasting tasks under real-world constraints. Full article

This paper presents Laor Initialization, an innovative weight initialization technique for deep neural networks that utilizes forward-pass error feedback in conjunction with k-means clustering to optimize the initial weights. In contrast to traditional methods, Laor adopts a data-driven approach that enhances convergence’s stability and efficiency. The method was assessed using various datasets, including a gold price time series, MNIST, and CIFAR-10 across the CNN and LSTM architectures. The results indicate that the Laor Initialization achieved the lowest K-fold cross-validation RMSE (0.00686), surpassing Xavier, He, and Random. Laor demonstrated a high convergence success (final RMSE = 0.00822) and the narrowest interquartile range (IQR), indicating superior stability. Gradient analysis confirmed Laor’s robustness, achieving the lowest coefficients of variation (CV = 0.2230 for MNIST, 0.3448 for CIFAR-10, and 0.5997 for gold price) with zero vanishing layers in the CNNs. Laor achieved a 24% reduction in CPU training time for the Gold price data and the fastest runtime on MNIST (340.69 s), while maintaining efficiency on CIFAR-10 (317.30 s). It performed optimally with a batch size of 32 and a learning rate between 0.001 and 0.01. These findings establish Laor as a robust alternative to conventional methods, suitable for moderately deep architectures. Future research should focus on dynamic variance scaling and adaptive clustering. Full article

Laurate (LA⁻)-intercalated nickel–chromium-layered double hydroxides (LDHs) were synthesized using the co-precipitation method and investigated as a potential photocatalyst for methylene orange (MO) degradation. For comparison, a series of LDHs with various molar ratios of Ni²⁺(or Mg²⁺)/Cr³⁺(or Fe³⁺)/LA⁻(or CO3²⁻) were prepared. X−ray diffraction (XRD) and element analysis showed that Ni/Cr(2/1)−1.0 LA LDH had the most ordered crystal structure, and showed the same photocatalytic decolorization performance as Mg/Cr(2/1)−1.0LA LDH towards MO, which was significantly superior to Ni/Cr−CO₃ LDH, Ni/Fe(2/1)−1.0LA LDH, and Ni/Cr−CO₃ LDH with LA⁻, and Cr³⁺ with LA⁻. The photocatalytic removal rate of MO with the initial concentration of 100 mg/L by Ni/Cr(2/1)−1.0LA LDH (0.5 g/L) could be up to 80% with UV light irradiation for 3 h, which was almost twice higher than that of the sorption test. The photocatalytic reaction was in accordance with the pseudo-first-order kinetics, which implied that the catalytic process took place on the surface of the catalyst. All the results indicate the photodegradation of MO by Ni/Cr−LA LDHs was enhanced by the sorption of MO onto the intercalated LA⁻ in the interlayer. The free radical capture experiments suggest that the main role of the photocatalytic mechanism of Ni/Cr−LA LDHs could be the •O₂⁻ with high oxidation activity produced by the electron-hole pairs of LDH, as excited by UV light. Additionally, the •O₂⁻ further reacted with the adjacent MO molecule pre-sorbed on the intercalated LA. Full article