Deep learning

Transfer of learning

Mobile robot

Meta learning (computer science)

Multi-task learning

Active learning (machine learning)

Online machine learning

Generalization error

Machine learning

Wake-sleep algorithm

Artificial intelligence

Management

Robot learning

Economics

Instance-based learning

Set (abstract data type)

Programming language

Computer science

Task (project management)

Unsupervised learning

Artificial neural network

Inductive transfer

Robot

Meta-Learning is a subarea of Machine Learning that aims to take advantage of prior knowledge to learn faster and with fewer data. There are different scenarios where meta-learning can be applied, and one of the most common is algorithm recommendation, where previous experience on applying machine learning algorithms for several datasets can be used to learn which algorithm, from a set of options, would be more suitable for a new dataset. Perhaps the most popular form of meta-learning is transfer learning, which consists of transferring knowledge acquired by a machine learning algorithm in a previous learning task to increase its performance faster in another and similar task. Transfer Learning has been widely applied in a variety of complex tasks such as image classification, machine translation and speech recognition, achieving remarkable results. Although transfer learning is very used in traditional or base-learning, it is still unknown if it is useful in a meta-learning setup. For that purpose, in this paper, we investigate the effects of transferring knowledge in the meta-level instead of base-level. Thus, we train a neural network on meta-datasets related to algorithm recommendation, and then using transfer learning, we reuse the knowledge learned by the neural network in other similar datasets from the same domain, to verify how transferable is the acquired meta-knowledge.

Transfer Learning for Algorithm Recommendation