On universal transfer learning

On Universal Transfer Learning

In transfer learning the aim is to solve new learning tasks using fewer examples by using information gained from solving related tasks. Existing transfer learning methods have been used successfully in practice and PAC analysis of these methods have been developed. But the key notion of relatedness between tasks has not yet been defined clearly, which makes it difficult to understand, let alon...

Learning More Universal Representations for Transfer-Learning

Transfer learning is commonly used to address the problem of the prohibitive need in annotated data when one want to classify visual content with a Convolutional Neural Network (CNN). We address the problem of the universality of the CNN-based representation of images in such a context. The state-of-the-art consists in diversifying the source problem on which the CNN is learned. It reduces the ...

On Universal Learning Algorithms

Discriminative Transfer Learning on Manifold

Collective matrix factorization has achieved a remarkable success in document classification in the literature of transfer learning. However, the learned latent factors still suffer from the divergence between different domains and thus are usually not discriminative for an appropriate assignment of category labels. Based on these observations, we impose a discriminative regression model over t...

Universal Learning Machines

All existing learning methods have particular bias that makes them suitable for specific kind of problems. Universal Learning Machine (ULM) should find the simplest data model for arbitrary data distributions. Several ways to create ULMs are outlined, and an algorithm based on creation of new global and local features combined with meta-learning is introduced. This algorithm is able to find sim...