Chapter 14 – Preparing the Input of Chatbots with Restricted Boltzmann Machines (RBMs) and Principal Component Analysis (PCA)
- RBMs are based on directed graphs. (Yes | No)
No. RBM graphs are undirected, unsupervised, and memoryless, and the decision-making is based on random calculations.
- The hidden units of an RBM are generally connected to one another. (Yes | No)
No. The hidden units of an RBM are not generally connected to each other.
- Random sampling is not used in an RBM. (Yes | No)
No. False. Gibbs random sampling is frequently applied to RBMs.
- PCA transforms data into higher dimensions. (Yes | No)
Yes. The whole point of PCA is to transform data into a lower number of dimensions in higher abstraction dimensions (key dimensions isolated) to find the principal component (highest eigenvalue of a covariance matrix), then the second highest, down to the lowest values.
- In a covariance...
