HMM Hidden Markov Model Source Code with Training Implementation
HMM Hidden Markov Model source code featuring model training capabilities with Baum-Welch algorithm implementation
LeNet-5 Training on MNIST Dataset with Enhanced Implementation
This resource implements the LeNet-5 architecture for the MNIST dataset, adapting the original network structure by modifying input dimensions to 28×28 pixels. The implementation draws inspiration from UFLDL tutorials and R. B. Palm's CNN codebase. Key modifications include full connectivity between C3 and S4 feature maps, achieving 99.1% accuracy through optimized training procedures with data augmentation and regularization techniques.
Echo State Network Implementation with Training and Testing Functions
Implementation of training and testing functionality for Echo State Networks in MATLAB environment
Neural Network Training Using Genetic Algorithm
MATLAB implementation for training neural networks with genetic algorithms to overcome local optima issues in neural network optimization, featuring population-based parameter evolution and fitness evaluation techniques.
HOG Pedestrian Detection
Implementation of pedestrian detection using HOG algorithm, with required data provided in *.dat files. Although positive and negative training samples are not included, users can train their own models and integrate them into the project to detect pedestrians in static images.
The RBF Neural Network: A Three-Layer Feedforward Architecture with a Single Hidden Layer
The RBF (Radial Basis Function) neural network is a three-layer feedforward structure consisting of an input layer, a hidden layer, and an output layer. This code implementation focuses on constructing and training an RBF neural network model, featuring algorithmic explanations for key components such as radial basis function calculations, weight optimization, and training methodologies.
Optimizing BP Neural Network Weights and Thresholds Using Genetic Algorithms
Training BP Neural Network Weights and Thresholds with Genetic Algorithm Optimization
Using Particle Swarm Optimization to Train Neural Network Parameters
This package implements Particle Swarm Optimization (PSO) for training neural network parameters. Simply run demoPSOnet.m to observe dynamic 2D visualization of the optimization process, where particle positions represent potential neural network weight configurations and their movement reflects the PSO algorithm's search mechanism through solution space.
Training Speech Signals with Baum Algorithm in HMM Models for Speech Recognition using MATLAB
MATLAB source code implementation of Baum algorithm for training speech signals in Hidden Markov Model (HMM) based speech recognition systems
MATLAB Implementation for Training RBF Neural Network Using Data Center Clustering Method
This source code implements RBF network training in MATLAB using a data center clustering approach, without relying on MATLAB's built-in training functions