POGD: Gradient Descent with New Stochastic Rules
This is an incremental improvement for machine learning practitioners seeking faster and more robust optimization in neural network training.
The paper tackles the problem of improving training speed and avoiding local minima in gradient descent by integrating particle swarm optimization principles, resulting in an adaptive learning algorithm tested on MNIST and CIFAR-10 datasets.
There introduce Particle Optimized Gradient Descent (POGD), an algorithm based on the gradient descent but integrates the particle swarm optimization (PSO) principle to achieve the iteration. From the experiments, this algorithm has adaptive learning ability. The experiments in this paper mainly focus on the training speed to reach the target value and the ability to prevent the local minimum. The experiments in this paper are achieved by the convolutional neural network (CNN) image classification on the MNIST and cifar-10 datasets.