Jack2032's starred repositories
Transfer-Learning-Library
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
deep-learning-dynamics-paper-list
This is a list of peer-reviewed representative papers on deep learning dynamics (optimization dynamics of neural networks). The success of deep learning attributes to both network architecture and stochastic optimization. Thus, deep learning dynamics play an essentially important role in theoretical foundation of deep learning.
Recurrent-Fuzzy-Neural-Network
MFRFNN: Multi-Functional Recurrent Fuzzy Neural Network for Chaotic Time Series Prediction
data_structures_and_algorithm
Data Structures and Algorithm Analysis in C++ (4th) Mark Allen Weiss 数据结构与算法分析（C++）第四版
Underwater-Acoustic-Target-Classification-Based-on-Dense-Convolutional-Neural-Network
In oceanic remote sensing operations, underwater acoustic target recognition is always a difficult and extremely important task of sonar systems, especially in the condition of complex sound wave propagation characteristics. Expensively learning recognition model for big data analysis is typically an obstacle for most traditional machine learning (ML) algorithms, whereas convolutional neural network (CNN), a type of deep neural network, can automatically extract features for accurate classification. In this study, we propose an approach using a dense CNN model for underwater target recognition. The network architecture is designed to cleverly re-use all former feature maps to optimize classification rate under various impaired conditions while satisfying low computational cost. In addition, instead of using time-frequency spectrogram images, the proposed scheme allows directly utilizing original audio signal in time domain as the network input data. Based on the experimental results evaluated on the real-world dataset of passive sonar, our classification model achieves the overall accuracy of 98.85$\%$ at 0 dB signal-to-noise ratio (SNR) and outperforms traditional ML techniques, as well as other state-of-the-art CNN models.
Evolving-CNNs-using-GA
Evolving Architectures for Convolutional Neural Networks using the Genetic Algorithm
Maritime-Weather-Forecaster
Hybrid Maritime Weather Forecaster Using Optimized of Neural Networks and Type-2 Fuzzy Logic
Evolutionary-neural-networks
Simultaneous optimization of the weights and architecture of neural networks (various optimization methods)
optimization-with-GA
Neural Network Architecture Optimization using Genetic Algorithm
Neural-Network-Optimizer
Optimization of neural networks using genetic algorithms to choose the best architecture
Optimizing-ANN-architecture
The project utilizes genetic algorithms to optimize the architecture of Artificial Neural Networks (ANN) conducting regression analysis on monochromatic laboratory figures
Optimization-of-Neural-Network-Architectures
Matlab programs to find optimal architectures of neural networks (multilayer perceptrons) for detecting loss of coolant accidents (LOCA) of a nuclear power plant (NPP) by training a number of network architectures on a transient dataset of LOCA. The transient dataset is not available to the public due to security issues. The neural networks take 37 inputs (representing 37 signals e.g. pressure, temperature and flow rates etc. of the primary heat transport of a NPP) and output the size of a break on the inlet header of the primary heat transport of the NPP. The size of a break is defined to be the double cross-sectional area of the inlet header and in the range 0% and 200% where 0% is no break and 200% is the complete rupture of the inlet header. The networks output a value between 0 (i.e. 0%) and 200 (i.e. 200%).