Training a deeper network (for example, adding additional layers to the network) allows the network to fit more complex functions and thus almost always results in lower training error. For this question, assume we’re referring to “plain” networks.

The motivation of Residual Networks is that very deep networks are so good at fitting complex functions that when training them we almost always overfit the training data. True/False?

Question 4.Regarding CNN Deep Learning Architectures for Computer Vision, please discussand explain the following concepts.(a) The Universal Approximation Theorem states that a 2-layer network canrepresent any computational problem to an arbitrary degree of accuracy.Why then is there a need to look at deeper networks?(b) Why is there a need for non-linear activation functions between layers?(c) Why do we use a loss function for training instead of a more intuitivemetric such as accuracy?(d) With respect to image data augmentation, how does fastai presizing workand why is it advantageous?(e) What is fine tuning and how is it used? What are the advantages of finetuning over training from scratch?(10 marks)(Part B: Total 40 marks)

In the best scenario when adding a ResNet block it will learn to approximate the identity function after a lot of training, helping improve the overall performance of the network. True/False?

Deep learning is a subset of machine learning algorithms that uses multiple layers to progressively extract information from the raw input to give better output.Select one:a. Trueb. False

A neural network is being trained to classify images of handwritten digits. The network consists of multiple hidden layers with a large number of neurons in each layer. However, during training, the network converges extremely long, and the training loss remains high. What could be a possible solution to this problem?a)Add more hidden layersb)Apply batch normalizationc)Reduce the number of neurons in each layerd)Increase the learning rate