Artificial Intelligence: Question 10
Syllabus 18.1
A phone manufacturer records, for thousands of batteries, the number of charge cycles each battery has completed and its remaining capacity, as a percentage of its original capacity. It trains a model on these paired records to predict the remaining capacity of a new battery from its number of completed charge cycles.
Which method is being used by this model to make its prediction?
Show worked solution Hide worked solution
Worked solution
Identifying the method
Every past record already pairs a number of charge cycles with a known, measured remaining capacity, and the value the model predicts, remaining capacity as a percentage, is a continuous number, not one of a small set of named labels.
Predicting a continuous numeric value from training data in this way is exactly what a regression method does.
Why the other options are wrong
- A (unsupervised learning): unsupervised learning trains on data with no known correct output attached. Here, every past battery record already states its actual remaining capacity, so this is not the case.
- B (reinforcement learning): reinforcement learning involves an agent taking actions and learning from reward or penalty feedback received through trial and error. There is no agent taking actions and no reward signal here, only a fixed set of past battery records.
- C (deep learning): deep learning specifically refers to a neural network built with many hidden layers. Nothing in the scenario states that such a network is being used. The size of the dataset alone does not make a task “deep learning”.
Final answer
D. This is a regression method, because the model predicts a continuous numeric value (remaining battery capacity, as a percentage) from the training data pairs.