Abstract: The prediction of molten iron silicon content ([Si]) is crucial for blast furnace operation. Nowadays, neural networks are emerging as the most advanced model for [Si] prediction tasks.

Quantum-inspired Leaky Integrate-and-Fire (QLIF) neurons for PyTorch, adaptive thresholds, dynamic spike probabilities, synaptic plasticity, neuromodulation, and optional qubit-based spike decisions.

Abstract: In the era of artificial intelligence, the complexity and diversity of data have posed unprecedented challenges for prediction tasks. Fuzzy information granules (FIGs) have emerged as a ...

An evnet driven model that uses financial time series data with New York Times information to form a LSTM recurrent neural network. There are 3 models. The first 2 models are based on price and volume ...

Learn how to build a fully connected, feedforward deep neural network from scratch in Python! This tutorial covers the theory, forward propagation, backpropagation, and coding step by step for a hands ...

Electroencephalography (EEG) and functional Magnetic Resonance Imaging (fMRI) are two widely used neuroimaging techniques, with complementary strengths and weaknesses. Predicting fMRI activity from ...

State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China ...

The Supporting Information is available free of charge at https://pubs.acs.org/doi/10.1021/acs.jcim.5c01525. Efficiency analysis of different normalization strategies ...

The rapid evolution of neural network methodologies has significantly improved the prediction of respiratory motion, which is critical for the precision of radiotherapy and robotic-assisted surgical ...