Single-Head Lifelong Learning Based on Distilling Knowledge

The Need of Lifelong Learning in the Knowledge-Based Society

Distilling Model Knowledge

Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and hard to integrate into larger systems. Ideally, we would like to replace such cumbersome models with simpler models that perform equally well. In this thesis, we study knowledge distillation, the idea of extracting the...

Lifelong Machine Learning Lifelong Machine Learning

Lifelong machine learning (or lifelong learning) is an advanced machine learning paradigm that learns continuously, accumulates the knowledge learned in previous tasks, and uses it to help future learning. In the process, the learner becomes more and more knowledgeable and effective at learning. This learning ability is one of the hallmarks of human intelligence. However, the current dominant m...

Game-Based Learning in Universities and Lifelong Learning: "UniGame: Social Skills and Knowledge Training" Game Concept

How to design effective learning opportunities? Why is learning by experience often more efficient than learning by studying? How to provide the learning experiences needed to respond to current challenges? Using computer games and games in general for educational purposes offers a variety of knowledge presentations and creates opportunities to apply the knowledge within a virtual world, thus s...

Lifelong Learning for Lifelong Employment

SOMEONE ASKED ME recently, “How do we keep 40-year-old software developers employed?” At rst I was puzzled. I had little clue this was a problem. Isn’t there more demand than supply for software developers? However, imagine a software developer who graduates from a good engineering school and gets a good job in a large high-tech company. He marries and raises a family, is good at barbecue, runs...