Mohammad Rostami

Transfer Learning through Embedding Spaces

• Gebundenes Buch

Produktbeschreibung

Transfer Learning through Embedding Spaces provides a brief background on transfer learning and then focus on the idea of transferring knowledge through intermediate embedding spaces. The idea is to couple and relate different learning through embedding spaces that encode task-level relations and similarities.

Produktdetails

• Verlag: Taylor and Francis
• Seitenzahl: 198
• Erscheinungstermin: 29. Juni 2021
• Englisch
• Abmessung: 254mm x 178mm x 14mm
• Gewicht: 603g
• ISBN-13: 9780367699055
• ISBN-10: 0367699052
• Artikelnr.: 62184995

Autorenporträt

Mohammad Rostami is a computer scientist at USC Information Sciences Institute. He is a graduate of the University of Pennsylvania, University of Waterloo, and Sharif University of Technology. His research area includes continual machine learning and learning in data scarce regimes.

Inhaltsangabe

Introduction. Background and Related Work. Zero-Shot Image Classification
through Coupled Visual and Semantic Embedding Spaces. Learning a
Discriminative Embedding for Unsupervised Domain Adaptation. Few-Shot Image
Classification through Coupled Embedding Spaces. Cross-Task Knowledge
Transfer. Lifelong Zero-Shot Learning Using High-Level Task Descriptors.
Complementary Learning Systems Theory for Tackling Catastrophic Forgetting.
Continual Concept Learning. Collective Lifelong Learning for Multi-Agent
Networks. Concluding Remarks and Potential Future Research Directions.