Abstract / truncated to 115 words (read the full abstract)

The unprecedented processing demand, posed by the explosion of big data, challenges researchers to design efficient and adaptive machine learning algorithms that do not require persistent retraining and avoid learning redundant information. Inspired from learning techniques of intelligent biological agents, identifying transferable knowledge across learning problems has been a significant research focus to improve machine learning algorithms. In this thesis, we address the challenges of knowledge transfer through embedding spaces that capture and store hierarchical knowledge. In the first part of the thesis, we focus on the problem of cross-domain knowledge transfer. We first address zero-shot image classification, where the goal is to identify images from unseen classes using semantic descriptions of these classes. We ... toggle 9 keywords

embedding space – zero-shot learning – domain adaptation – lifelong learning – multitask learning – catastrophic forgetting – continual learning – distributed learning – collective learning

Follow @eurasip