Questions and Exercises
Check your level of understanding of the concepts explored in this chapter by answering the following questions:
- Why are LSTM units suitable for time series analysis?
a). Because they are faster than classic feedforward networks
b). Because they can remember past input tensors
c). Because they use gates
d). Because they have hidden states
- What is the data extraction option to use for partitioning in time series analysis?
a). Draw randomly
b). Take from top
c). Stratified Sampling
d). Linear Sampling
- What is a tensor?
a). A tensor is a two-dimensional vector.
b). A tensor is a k-dimensional vector.
c). A tensor is just a number.
d). A tensor is a sequence of numbers.
- What is the difference between in-sample and out-sample testing?
a). In-sample testing uses the real past values from the test set to make the predictions. Out-sample testing uses past prediction values to make new predictions.
b). In-sample testing is more realistic than out-sample testing...
