What are the factors in selecting the depth of neural networks?1. Type of neural network (eg. MLP, CNN, etc)2. Input data3. Computation power, i.e. Hardware capabilities and software capabilities4. Learning Rate5. The output function to mapQuestion 6Answera.1, 3, 4, 5b.All of thesec.1, 2, 4, 5d.2, 3, 4, 5

Which of the following options is the key factor that led the return of neural networks?Group of answer choicesthe back-propagation learning algorithmDramatically increased Computational power (Cloud computing)World Wide WebBig data (five Vs)Deep learning algorithms

The _______algorithm figures out the best depth limit by slowly raising it until it reaches the desired depthUniform cost searchIterative deepening depth-firstBidirectional SearchDepth-first Search

A Neural Network consists of an Input Layer, Hidden Layer and an Output Layer. Which of the given options forms the important components of the Hidden Layer?Select an option Clear ResponseWeights and BiasesWeights and Input neuronBiases and Input neuronWeights and Output neurons

Which of the following are true about Depth wise-separable convolutions? (Choose all that apply)

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)