AutoML means using ML to create better ML models.
Meta-learning improves the learning of sophisticated tasks by reusing knowledge.
3 main forms of meta-learning relevant to AutoML⬇️
Meta-learning improves the learning of sophisticated tasks by reusing knowledge.
3 main forms of meta-learning relevant to AutoML⬇️
1) Based on Model Evaluations
Learn new tasks based on the configuration of models based on similar tasks.
Configuration = hyperparameter settings, pipeline, and/or network architecture components.
Learn new tasks based on the configuration of models based on similar tasks.
Configuration = hyperparameter settings, pipeline, and/or network architecture components.
2) Based on Task Properties
Transfer knowledge between empirically similar tasks.
This method describes tasks as a set of meta-features and predicts the outcome of similar tasks by evaluating the distance with its meta-feature vector and other tasks.
Transfer knowledge between empirically similar tasks.
This method describes tasks as a set of meta-features and predicts the outcome of similar tasks by evaluating the distance with its meta-feature vector and other tasks.
3) Based on Previous Models
Learn from prior ML models themselves, using aspects such as their structure and learned model parameters.
It has major overlaps with transfer learning. It focuses on transferring trained model parameters between tasks.
Learn from prior ML models themselves, using aspects such as their structure and learned model parameters.
It has major overlaps with transfer learning. It focuses on transferring trained model parameters between tasks.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
