Analytical Study on Artificial Neural Network Learning Algorithms and Technique

The artificial neural networks are widely used to support the human decision capabilities, avoiding inconsistency in practice and errors based on lack of experience. In this paper we have explored various learning rules in artificial neural networks like preceptron learning, error correction, hebbian and competition learning rules are explored. Learning rules are algorithms which direct changes in the weights of the connections in a network.

They are incorporating an error reduction procedure by employing the difference between the desired output and an actual output to change its weights during training. The learning rule is typically applied repeatedly to the same set of training inputs across a large number of epochs with error gradually reduced across epochs as the weights are fine-tuned. This paper also focuses on one of the neural network technique called Multilayer Perceptron (MLP) along with its applications and advantages and drawbacks.