Exam AWS Certified AI Practitioner AIF-C01 topic 1 question 7 discussion

Transfer learning allows you to leverage pre-trained models (which have already been trained on large datasets) and adapt them for new, related tasks with minimal additional training. This strategy is highly efficient because it saves time and computational resources compared to training a model from scratch. By fine-tuning the pre-trained model on a smaller dataset specific to the new task, the model can learn task-specific features while maintaining the general knowledge it acquired during its initial training.

It is clearly B. The number of epochs is not related to that issue while the (un)supervised learning is used for training a new model, which is totally different from adapting a pre-trained model to create a new model.

B: Use transfer learning. Explanation: Transfer learning is a machine learning strategy that leverages pre-trained models and adapts them to new but related tasks. This allows the company to avoid building models from scratch, significantly reducing the time and resources required for training. By fine-tuning the pre-trained model on domain-specific data, the company can achieve high performance for the new task without starting from the beginning.

Transfer learning

Transfer learning involves taking a pre-trained model, which has been trained on a large dataset, and adapting it to a new, related task. This approach offers several advantages:

TL where a model pre-trained on one task is fine-tuned for a new, related task.