# What's the benefit for using a Kalman filter for training a neural network compared to other optimization algorithms?

I found a paper about using an Unscented Kalman Filter(UKF) for traning a neural network.

The UKF filter is modified so it works for parameter estimation. Assume that we have a neural network model $$\hat d_k = G(x_k, W_k)$$ where $$G$$ is the neural network, $$x_k$$ is the input vector, $$W_k$$ is the parameter gain matrix and $$\hat d_k$$ is the output vector.

This paper counts servral methods to train a neural network.

• Quasi-Newton
• UKF parameter estimation

So my questions for you are:

1. What's the benefit for using a kalman filter for training a neural network compared to other optimization algorithms?

2. I remember that I have been using gradient descent methods and they work, but I have always used regularization. Is that due to the noise in the data?

3. If I'm using a UKF-filter as parameter estimation, I can avoid regularization then?

4. Is this UKF parameter estimation algorithm only made for 1 layer neural network, or can it be used for deep neural networks as well?

• Hello, asking multiple questions in a single post is not recommended. Please try to split the questions into multiple posts. Sep 14 at 21:53
• @hanugm Yes! I created a new question with only 1 question. ai.stackexchange.com/questions/31701/… Sep 15 at 22:41