Evaluate the impact of an AI application used in the real world. (case study) : Working with Flower Images: Case Study -

The video tutorial emphasizes the importance of normalization in image processing, particularly in smoothing the training process. It explains how data points with varying ranges can affect gradients during backpropagation, especially when using activation functions like sigmoid. The tutorial also addresses the issue of outliers and presents different normalization techniques, such as using percentiles and standard deviation. It highlights the need for appropriate normalization methods for different types of images, like natural and X-ray images, to ensure effective training outcomes.

Why is normalization considered an important preprocessing step in data processing?

What are the potential issues that can arise during backpropagation if normalization is not applied?

Explain the difference between using the sigmoid activation function and other activation functions in the context of normalization.

How does the presence of outliers affect the normalization process?

What is the formula for normalization using percentiles, and why is it preferred in certain cases?

What are the advantages of using the mean and standard deviation for normalization compared to dividing by 255?

Discuss the implications of not normalizing data before training a model.