IVY-TATA STEEL-ML-AUGUST 12

Which statement about Neural networks is true?

• optimize a convex cost function
• can be used for regression as well as classification
• always output values between 0 and 1
• can't used in an ensemble

What does back propagation for neural network training determines?

• error not represented by rest of the model
• inputs that are mapped to numerical output
• weights and residual represented by hidden layers
• error added to the each node of the data

Which of these are not a neural network layers?

• Hidden Layer
• Dense Layer
• Input Layer
• Bias Layer

What is the main motivation for using activation functions in ANN?

• Capturing complex non-linear patterns
• Transforming continuous values into "ON" (1) or "OFF" (0) values
• Help avoiding the vanishing gradient problem
• to activate each neurons individually.

A time series consists of:

• Short-term variations
• Long-term variations
• Irregular variations
• All of the above

Indicate which of the following an example of seasonal variations is:

• Death rate decreased due to advance in science
• The sale of air condition increases during summer
• Recovery in business
• Sudden causes by wars

Decomposition of time series is called:

• Historigram
• Analysis of time series
• Histogram
• Detrending

LSTM? What is that?

• LSTM networks are an extension for recurrent neural networks, which basically extends their memory. Therefore it is well suited to learn from important experiences that have very long time lags in between
• LSTM networks are an extension for recurrent neural networks, which basically extends their memory. Therefore it is well suited to learn from important experiences that have very low time lags in between
• LSTM networks are an extension for recurrent neural networks, which basically shorten their memory. Therefore it is well suited to learn from important experiences that have very low time lags in between
• LSTM networks are an extension for recurrent neural networks, which basically extends their memory. Therefore it is not recommended to use it, unless you are using a small Dataset.

In RNN´s there is a issue called 'Vanishing Gradients'. What is that?

• When the values of a gradient are too small and the model stops learning or takes way too long because of that.
• When the values of a gradient are too big and the model stops learning or takes way too long because of that.
• When the values of a gradient are too small and the model joins in a loop because of that.
• When the values of a gradient are too big and the model joins in a loop because of that.

Which of the following is an example of time series problem? 1. Estimating number of hotel rooms booking in next 6 months. 2. Estimating the total sales in next 3 years of an insurance company. 3. Estimating the number of calls for the next one week.

• Only 3
• 1 and 2
• 2 and 3
• 1 and 3
• 1,2 and 3