[Youtube]
Lifelong and human-like learning in foundation models. SNU AI Seminar. Seoul National University. Seoul, South Korea. 2024/12/05. [slides]
Lifelong and human-like learning in foundation models. Columbia University. New York, NY, USA. 2024/09/13. [slides]
Computer vision and deep learning: A primer. New York, NY, USA. 2024/06/04. [slides]
Lifelong and human-like learning in foundation models. Machine Learning Seminar. Flatiron Institute. New York, NY, USA. 2024/04/30. [slides]
Lifelong and human-like learning in foundation models. Smart Minds meet Smart Machines: AI for Science and Public Good. German Consulate General in New York. New York, NY, USA. 2024/04/08. [slides]
Lifelong learning in structured environments. American Statistical Association, Statistical Learning and Data Science Webinar. Virtual. 2023/10. [slides] [video]
Biologically plausible learning using local activity perturbation. University of British Columbia. Vancouver, BC, Canada. 2023/06. [slides]
Scaling forward gradient with local losses. Baylor College of Medicine, Journal Club Invited Talk. Houston, TX, USA. 2023/06. [slides]
Meta-learning within a lifetime. NeurIPS 2022 MetaLearn Workshop, Invited Talk. New Orleans, LA, USA. 2022/12. [slides] [video]
Biologically plausible learning using local activity perturbation. New York University, Center for Data Science. New York, NY, USA. 2022/10. [slides] [video]
Visual learning in the open world. 19th Conference on Robotics and Vision (CRV), Invited Symposium. Toronto, ON, Canada. 2022/06. [slides]
Visual learning in the open world. University of Oxford. Oxford, UK. 2021/11. [slides]
Visual learning in the open world. Google Brain. Toronto, ON, Canada. 2021/11. [slides]
Visual learning in the open world. Stanford University. Stanford, CA, USA. 2021/10. [slides]
Visual learning in the open world. Huawei. Markham, ON, Canada. 2021/09. [slides]
Steps towards making machine learning more natural. Job talk. 2021/02 - 2021/04. [slides]
A tutorial on few-shot learning and unsupervised representation learning. Vector Institute. Toronto, ON, Canada. 2021/01. [slides]
How can we apply few-shot learning? Vector Institute. Toronto, ON, Canada. 2020/10. [slides]
Towards continual and compositional few-shot learning. Stanford University. Stanford, CA, USA. 2020/10. [slides]
Towards continual and compositional few-shot learning. Brown University. Providence, RI, USA. 2020/09. [slides]
Towards continual and compositional few-shot learning. MIT. Cambridge, MA, USA. 2020/09. [slides] [video]
Towards continual and compositional few-shot learning. Mila. Montréal, QC, Canada. 2020/08. [slides]
Wandering within a world: Online contextualized few-shot learning (with M. Mozer). Google Brain. Montréal, QC, Canada. 2020/08. [slides]
Wandering within a world: Online contextualized few-shot learning. ICML 2020 Lifelong Learning Workshop. Virtual webinar. 2020/07. [slides]
Wandering within a world: Online contextualized few-shot learning. ICML 2020 Continual Learning Workshop. Virtual webinar. 2020/07. [slides]
Jointly learnable behavior and trajectory planning for self-driving vehicles. IROS 2019. Macau, China. 2019/11. [slides]
Meta-learning for more human-like learning algorithms. Columbia University, Department of Statistics. New York, NY, USA. 2019/10. [slides]
Learning to reweight examples for robust deep learning. CIFAR deep learning and reinforcement learning summer school. Toronto, Ontario, Canada. 2018/08. [slides]
Meta-learning for weakly supervised learning. INRIA Grenoble Rhône-Alpes. Grenoble, France. 2018/07. [slides]
Learning to reweight examples for robust deep learning. ICML 2018. Stockholm, Sweden. 2018/07. [slides] [video]
Meta-learning and learning to reweight examples. Max Planck Institute for Intelligent Systems. Tübingen, Germany. 2018/06. [slides]
Meta-learning for weakly supervised learning. NEC Laboratories America. Princeton, NJ, USA. 2018/06. [slides]
SBNet: Sparse blocks network for fast inference. Borealis AI Lab. Toronto, ON, Canada. 2018/02. [slides]
Meta-learning for semi-supervised few-shot classification. Vector Institute. Toronto, ON, Canada. 2017/11. [slides]
End-to-end instance segmentation with recurrent attention. CVPR 2017. Honolulu, HI, USA. 2017/07. [slides] [video]
Sequence-to-sequence deep learning with recurrent attention. Queen’s University. Kingston, ON, Canada. 2017/05. [slides]
Recurrent neural networks. CSC 2541 Guest Lecture. University of Toronto. Toronto, ON, Canada. 2017/01. [slides]