A data scientist uses SAS DLPy to define a recurrent neural network for time series forecasting. Which SAS DLPy layer type should be added to capture sequential dependencies?
Select an answer to reveal the explanation.
Short Explanation
You want the LSTM layer because it’s built to learn long-range sequential dependencies in time series data. Its gating mechanisms control information flow across time steps, and SAS DLPy supports it through the Recurrent layer class.
Full Explanation
The LSTM layer (RNN with Long Short-Term Memory cells) is correct because it is designed to learn long-range sequential dependencies in time series data by using gating mechanisms to control information flow across time steps. SAS DLPy supports LSTM layers via the Recurrent layer class. The Conv2d layer is a 2D convolutional layer for spatial data, not sequential time dependencies. The BatchNorm layer normalizes activations and is not a sequential dependency layer. The Reshape layer restructures tensor dimensions and has no learning parameters.