A Novel Method for improving accuracy in neural network by reinstating traditional back propagation technique

TL;DR

This paper introduces a new training method for neural networks that bypasses traditional back propagation, reducing computation and addressing vanishing gradients, leading to faster and more effective learning.

Contribution

It proposes an innovative instant parameter update technique that eliminates the need for gradient computation at each layer, improving training efficiency and performance.

Findings

Accelerates neural network training process

Prevents vanishing gradient problem effectively

Outperforms existing state-of-the-art methods on benchmarks

Abstract

Deep learning has revolutionized industries like computer vision, natural language processing, and speech recognition. However, back propagation, the main method for training deep neural networks, faces challenges like computational overhead and vanishing gradients. In this paper, we propose a novel instant parameter update methodology that eliminates the need for computing gradients at each layer. Our approach accelerates learning, avoids the vanishing gradient problem, and outperforms state-of-the-art methods on benchmark data sets. This research presents a promising direction for efficient and effective deep neural network training.