IAPP Artificial Intelligence Governance Professional (AIGP) — Question 27

All of the following are common optimization techniques in deep learning to determine weights that represent the strength of the connection between artificial neurons EXCEPT:

Answer options

• A. Gradient descent, which initially sets weights to arbitrary values, and then at each step changes them.
• B. Momentum, which improves the convergence speed and stability of neutral network training.
• C. Autoregression, which analyzes and makes predictions about time-series data.
• D. Backpropagation, which starts from the last layer working backwards.

Correct answer: C

Explanation

The correct answer is C because Autoregression is focused on time-series data analysis and prediction, not on weight optimization in neural networks. In contrast, Gradient descent, Momentum, and Backpropagation are all established techniques used to adjust and optimize weights in deep learning models.