Monthly Archives: November 2018
The case for lifelong learning Lifelong learning (also known as continual learning) is the problem of learning multiple consecutive tasks in a sequential manner where knowledge gained from previous tasks is retained and used for future learning . Living in … Continue reading
Meet us at the NIPS workshops were we will be presenting the following works:
- Sample-Efficient Imitation Learning via Generative Adversarial Nets (Lionel Blondé, Alexandros Kalousis), in the Deep RL and in the Imitation Learning and its Challenges in Robotics workshops.
- Continual Classification Learning Using Generative Models (Frantzeska Lavda, Jason Ramapuram, Magda Gregorova, Alexandros Kalousis), in the Continual Learning workshop.
- Variational Saccading: Efficient Inference for Large Resolution Images (Jason Ramapuram, Maurits Diephuis, Russ Webb, Alexandros Kalousis), in the Bayesian Deep Learning workshop.
Read the blog to know about the latest endeavours of the DMML group!
Generative Adversarial Imitation Learning (GAIL)  is a recent successful imitation learning architecture that exploits the adversarial training procedure introduced in Generative Adversarial Networks (GAN) . Albeit successful at generating behaviours similar to those demonstrated to the agent, GAIL suffers … Continue reading
Warm welcomes to our new colleague, Ye Yuan, who started his PhD with us in September 2018 to work on our gait project. Ye has got a master's degree in Computer Science from the Institute of Computing Technology of the University of Chinese Academy of Science and has got some experience with NLP and stock market predictions. We hope Ye will be a good fit for our team and that he will enjoy his PhDing in Geneva, Switzerland. Continue reading