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 and Infographic
Here's the deal — b is correct because LSTM (Long Short-Term Memory) layers are 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.
Full explanation below image
Full Explanation
B is correct because LSTM (Long Short-Term Memory) layers are 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. A (Conv2d) is a 2D convolutional layer for spatial data. C (BatchNorm) normalizes activations and is not a sequential dependency layer. D (Reshape) restructures tensor dimensions and has no learning parameters.