A Novel Method for improving accuracy in neural network by reinstating traditional back propagation technique
This work addresses efficiency and effectiveness in deep neural network training, potentially benefiting industries like computer vision and NLP, but appears incremental as it modifies an existing technique.
The paper tackles the challenges of back propagation in deep neural networks, such as computational overhead and vanishing gradients, by proposing a novel instant parameter update methodology that eliminates gradient computation at each layer, resulting in accelerated learning and outperforming state-of-the-art methods on benchmark datasets.
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.