Abstract:
Meta-learning, or learning-to-learn, has exploded in popularity. Meta-learning uses multiple learning episodes to improve the learning algorithm, unlike traditional AI approaches that start from scratch. This paradigm can address data, computation, and generalization bottlenecks in deep learning. This survey describes meta-learning today. Meta-learning is defined and compared to transfer learning and hyperparameter optimization. We then propose a more comprehensive taxonomy of meta-learning methods. Few-shot and reinforcement learning are promising meta-learning applications. Finally, we discuss remaining issues and promising research areas.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
