EXPERIMENTAL STUDY OF MACHINE LEARNING AND NEURAL NETWORKS USING DEEP LEARNING

Abstract

The emergence of neural network technology may be attributed to the continuous development of
neural network theory and its associated theories and technologies. This branch of intelligent control technology
has gained significant importance in recent years. An artificial neural network (ANN) is a kind of computational
model that exhibits nonlinearity and adaptability in its information processing capabilities. The system consists
of a very large quantity of processing units. In this research, the architecture of an intelligent system is designed
using an adaptable fuzzy neural network (FNN). Additionally, an activation function is implemented to include
information from the disciplines of computer science and languages. The diagram illustrating the neural
architecture of the network is shown in this figure. The machine learning model architecture was constructed
based on a recursive neural network using Deep learning , which forms the fundamental framework. The use of
the feature vector extraction technique and the normalization algorithm is necessary to meet the requirements of
the neural network model. The clustering approach is used to build a diverse set of learning styles by using the
feature vectors derived from various users' learning styles. Through the use of testing, the design of the
functional flow was established, therefore enabling the demonstration of the reliability of the Deep learning
model. The precise acquisition of language skills has the potential to activate specific regions of the brain,
resulting in enhanced Deep learning efficacy and increased aptitude for acquiring other languages