Timezone: »
Oral
Rapid Adaptation with Conditionally Shifted Neurons
Tsendsuren Munkhdalai · Xingdi Yuan · Soroush Mehri · Adam Trischler
Fri Jul 13 07:40 AM -- 07:50 AM (PDT) @ Victoria
We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons. We apply this mechanism in the framework of metalearning, where the aim is to replicate some of the flexibility of human learning in machines. Conditionally shifted neurons modify their activation values with task-specific shifts retrieved from a memory module, which is populated rapidly based on limited task experience. On metalearning benchmarks from the vision and language domains, models augmented with conditionally shifted neurons achieve state-of-the-art results.
Author Information
Tsendsuren Munkhdalai (Microsoft Research)
Xingdi Yuan (Microsoft Maluuba)
Soroush Mehri (Microsoft Research)
Adam Trischler (Microsoft Research)
Related Events (a corresponding poster, oral, or spotlight)
-
2018 Poster: Rapid Adaptation with Conditionally Shifted Neurons »
Fri. Jul 13th 04:15 -- 07:00 PM Room Hall B #33
More from the Same Authors
-
2022 Poster: Asking for Knowledge (AFK): Training RL Agents to Query External Knowledge Using Language »
Iou-Jen Liu · Xingdi Yuan · Marc-Alexandre Côté · Pierre-Yves Oudeyer · Alex Schwing -
2022 Spotlight: Asking for Knowledge (AFK): Training RL Agents to Query External Knowledge Using Language »
Iou-Jen Liu · Xingdi Yuan · Marc-Alexandre Côté · Pierre-Yves Oudeyer · Alex Schwing -
2018 Poster: Focused Hierarchical RNNs for Conditional Sequence Processing »
Rosemary Nan Ke · Konrad Zolna · Alessandro Sordoni · Zhouhan Lin · Adam Trischler · Yoshua Bengio · Joelle Pineau · Laurent Charlin · Christopher Pal -
2018 Oral: Focused Hierarchical RNNs for Conditional Sequence Processing »
Rosemary Nan Ke · Konrad Zolna · Alessandro Sordoni · Zhouhan Lin · Adam Trischler · Yoshua Bengio · Joelle Pineau · Laurent Charlin · Christopher Pal -
2017 Poster: Learning Algorithms for Active Learning »
Philip Bachman · Alessandro Sordoni · Adam Trischler -
2017 Talk: Learning Algorithms for Active Learning »
Philip Bachman · Alessandro Sordoni · Adam Trischler