Data Science and Machine Learning (Theory and Projects) A to Z - DNN and Deep Learning Basics: DNN Gradient Descent Stoc

The video tutorial covers different gradient descent methods: stochastic, mini batch, and batch gradient descent. It explains the bias term's role in neural networks, allowing hyperplanes to be positioned arbitrarily. The tutorial details how each gradient descent method works, their benefits, drawbacks, and computational requirements. Mini batch gradient descent is highlighted as a practical compromise. The video concludes with a preview of an animation and coding demonstration in the next video.

Which of the following is NOT a type of gradient descent method?

• Stochastic Gradient Descent

• Mini-batch Gradient Descent

• Batch Gradient Descent

• Random Gradient Descent

What is the primary role of the bias term in a neural network?

• To define the activation function

• To allow hyperplanes to be positioned arbitrarily

• To decrease the number of epochs

• To increase the learning rate

In batch gradient descent, how is the loss computed?

• On all examples at once

• On a random subset of examples

• On a single example

• On a mini-batch of examples

Which gradient descent method updates weights after each example?

• Batch Gradient Descent

• Stochastic Gradient Descent

• Mini-batch Gradient Descent

• None of the above

What is a key advantage of mini-batch gradient descent?

• It uses the entire dataset for each update

• It combines benefits of both batch and stochastic methods

• It always converges faster than other methods

• It requires no computational resources

Why might batch gradient descent require more computational resources?

• It uses a fixed learning rate

• It computes loss on the entire dataset

• It updates weights after each example

• It processes one example at a time

How does mini-batch gradient descent improve efficiency?

• By using the entire dataset for each update

• By using small batches for updates

• By using a single example for updates

• By reducing the learning rate