CT-AI · Question #69
You are evaluating the use of a highly accurate pre-trained model that is used widely in industry for a similar use case. There is an intention to apply transfer learning techniques to further…
The correct answer is D. The functional performance of the pre-trained model could be lower than stakeholders expect. When using a pre-trained model, especially one that is highly accurate and widely used in industry, it is less likely that the functional performance will be lower than expected, given that it has already been proven effective in similar use cases.
Question
You are evaluating the use of a highly accurate pre-trained model that is used widely in industry for a similar use case. There is an intention to apply transfer learning techniques to further customize the model. Which ONE of the following is the LEAST likely to be a significant risk with this approach?
Options
- AThe functional performance of the system may exhibit bias
- BThe system may be vulnerable to adversarial attacks inherited from the pre-trained model
- CDifferences in data preparation steps between the training of the pre-trained model and
- DThe functional performance of the pre-trained model could be lower than stakeholders expect
How the community answered
(17 responses)- A12% (2)
- B6% (1)
- C6% (1)
- D76% (13)
Explanation
When using a pre-trained model, especially one that is highly accurate and widely used in industry, it is less likely that the functional performance will be lower than expected, given that it has already been proven effective in similar use cases.
Topics
Community Discussion
No community discussion yet for this question.