Litcius/Paper detail

A Review of Optimization Algorithms for Training Neural Networks

Animesh Srivastava, Bhupender Singh Rawat, Gulbir Singh, Vivek Bhatnagar, Parveen Kumar Saini, Shiv Ashish Dhondiyal

202320 citationsDOI

Abstract

The selection of the optimization algorithm (optimizer) is one of the most essential endeavors in Deep Learning and across all categories of Neural Networks. It's a matter of experimenting by making mistakes and learning from them. In this research, we will conduct experiments using 7 of the most common optimization algorithms, namely: Stochastic Gradient Descent, Root Mean Square Propagation, Adaptive Gradient Algorithm, Adadelta, Adaptive Moment Estimation, Adamax, and Nadam on MNIST datasets, to determine which one provides the deep neural network with the highest accuracy and performance. A data scientist will benefit from the insightful analysis provided by this study in selecting the most appropriate optimizer to use while modeling their deep neural network.

Topics & Concepts

MNIST databaseComputer scienceArtificial neural networkStochastic gradient descentArtificial intelligenceGradient descentMachine learningSelection (genetic algorithm)Moment (physics)BackpropagationOptimization algorithmDeep learningAlgorithmDeep neural networksAdaptive optimizationStochastic neural networkMathematical optimizationTime delay neural networkMathematicsPhysicsClassical mechanicsOperating systemAdvanced Neural Network ApplicationsComputer Science and EngineeringVehicle License Plate Recognition
A Review of Optimization Algorithms for Training Neural Networks | Litcius