A Comprehensive Study on Optimization Strategies for Gradient Descent In Deep Learning
This paper aims to introduce optimization strategies for gradient descent to deep learning practitioners, serving as an incremental overview of existing methods.
This paper provides an introduction to various optimization strategies for gradient descent in deep learning, addressing the slowness and inaccuracy of regular gradient descent. It discusses the architecture of these algorithms and general optimization techniques for neural networks.
One of the most important parts of Artificial Neural Networks is minimizing the loss functions which tells us how good or bad our model is. To minimize these losses we need to tune the weights and biases. Also to calculate the minimum value of a function we need gradient. And to update our weights we need gradient descent. But there are some problems with regular gradient descent ie. it is quite slow and not that accurate. This article aims to give an introduction to optimization strategies to gradient descent. In addition, we shall also discuss the architecture of these algorithms and further optimization of Neural Networks in general