MASTERING THE MACHINE

1. A programmer builds a bot capable of playing tic-tac-toe against human opponents.  The programmer enumerates every potential game board configuration and hard-codes the optimal move which the bot should take.  This is an example of

• A. Rule based logic

• B. Graph based logic

• C. Code based logic

• D. Hash based logic

1. The same activation function must be used in every layer of the neural network.

• 1. True

• 1. False

1. The same number of nodes must be used in each layer.

• True

• False

1. What was the name of the first device that was based on the principle of the artificial neuron?

• 1. Megatron

• 1. Mark II Galvatron

• 1. Iron Man Mark III armour (Jarvis Integrated)

• 1. Mark I Perceptron

1. What is deep learning?

• A type of machine learning that uses a single layer of nodes.  

• A type of machine learning that uses multiple layers of nodes.  

• A method for data storage and retrieval.  

• A technique for image compression.

1. Which of the following is a common activation function used in deep learning?

• Softmax  

• ReLU  

• Sigmoid  

• All of the above

1. What is the purpose of an activation function in a neural network?

• To update the weights during training

• To calculate the loss function  

• To introduce non-linearity into the network  

• To initialize the weights of the network  

1. What is backpropagation used for in neural networks?

• To update the weights based on the error  

• To initialize the neural network weights

• To forward propagate the input through the network  

• To normalize the input data  

1. Which of the following statements about Convolutional Neural Networks (CNNs) is true?

• CNNs are primarily used for natural language processing.  

  
  

• CNNs are invariant to the spatial hierarchy of features. 

• CNNs are most commonly used for image and video recognition.  

• CNNs do not use pooling layers.

1. What is a common method to train deep learning models?

• K-means clustering  

• Gradient Descent  

• Linear Regression  

• Apriori Algorithm