4. Deep Learning and Variants_Session 4_20240127 - Artificial Neural Networks Learning Methods

What defines 'Deep' in the context of neural networks?

In Deep Learning, what is the main benefit of using multiple layers?

Which theorem states that an artificial neural network with a single hidden layer can approximate any continuous function on compact subsets of Rn with infinite neurons?

Why might visualization become difficult in a shallow network when dealing with unstructured data like an image dataset?

What is a potential issue with using a very large number of neurons in just one hidden layer of a neural network?

How does having a single hidden layer network with a large number of neurons lead to 0% training error?

Which type of problem can benefit from using deep neural networks instead of shallow networks?

What role do hidden layers play in deep learning neural networks?

What is one of the issues faced when using more layers in deep networks?

Why does a (k−1)-layer network require an exponentially large number of hidden units to represent a function that a k-layer network can represent compactly?

What is one of the central problems in Machine Learning according to the text?

Why does gradient descent become very inefficient in deeper networks?

What happens to the gradients as more hidden layers are added to a deep network?

Why does adding more layers to a network not always lead to better performance?

What is a major issue with deep learning highlighted in the text?

What is the derivative of a sigmoid function highlighted as in the text?

What percentage of training accuracy is highlighted in the text?

Which issue makes optimization difficult for deep learning networks?

What type of points are mentioned as problematic in high-dimensional spaces?

What combination is described as deadly for neural networks in the text?

Why is finding a minimum over the surface difficult in deep learning optimization?

What is a challenge that arises from each sigmoid derivative being less than 0.3?

What is the purpose of back-propagation in Artificial Neural Networks (ANN)?

What does the term 'Back-propagation' stand for in Artificial Neural Networks?

Who popularized the Back-propagation method in Neural Networks?

What problem can occur due to vanishing gradients in a Neural Network with many layers?

In simple cases, what action should be taken if the output of an Artificial Neural Network is too high?

What does ANN stand for in the context of Artificial Neural Networks?

'Backpropagation' led to a renaissance in which area?

'𝑤𝑡+1 𝜕𝐸 = 𝑤𝑡 − 𝛼 𝜕𝑊' represents which concept in Artificial Neural Networks?