강연 / 세미나
MINDS Seminar on Machine Learning
| 분야Field | |||
|---|---|---|---|
| 날짜Date | 2023-11-14 ~ 2023-11-14 | 시간Time | 17:00 ~ 18:00 |
| 장소Place | Math Bldg.404&Online streaming (Zoom) | 초청자Host | |
| 연사Speaker | Eren Mehmet Kıral | 소속Affiliation | (Keio University, Japan) |
| TOPIC | MINDS Seminar on Machine Learning | ||
| 소개 및 안내사항Content | Title : Lie Group updates for Learning Distributions on Machine Learning Parameters speaker : Eren Mehmet Kıral (Keio University, Japan) abstract : I will talk about our recent paper https://arxiv.org/abs/2303.04397 with Thomas Möllenhoff and Emtiyaz Khan, and other related results. Bayesian Learning learns a distribution over the model parameters, allowing for different descriptions of the same data. This is (contrary to classical learning which "bets-it-all" on a single set of parameters in describing a given dataset and making predictions. We focus on classes of distributions which have a transitive Lie group action on them given by pushforwards of an action on the parameter space. I will also specialize to a few concrete Lie groups and show distinct learning behavior. link : https://us06web.zoom.us/j/6888961076?pwd=ejYxN05jNmhUa25PU2JzSUJvQ1haQT09 |
||
| 학회명Field | MINDS Seminar on Machine Learning | ||
|---|---|---|---|
| 날짜Date | 2023-11-14 ~ 2023-11-14 | 시간Time | 17:00 ~ 18:00 |
| 장소Place | Math Bldg.404&Online streaming (Zoom) | 초청자Host | |
| 소개 및 안내사항Content | Title : Lie Group updates for Learning Distributions on Machine Learning Parameters speaker : Eren Mehmet Kıral (Keio University, Japan) abstract : I will talk about our recent paper https://arxiv.org/abs/2303.04397 with Thomas Möllenhoff and Emtiyaz Khan, and other related results. Bayesian Learning learns a distribution over the model parameters, allowing for different descriptions of the same data. This is (contrary to classical learning which "bets-it-all" on a single set of parameters in describing a given dataset and making predictions. We focus on classes of distributions which have a transitive Lie group action on them given by pushforwards of an action on the parameter space. I will also specialize to a few concrete Lie groups and show distinct learning behavior. link : https://us06web.zoom.us/j/6888961076?pwd=ejYxN05jNmhUa25PU2JzSUJvQ1haQT09 |
||
| 성명Field | MINDS Seminar on Machine Learning | ||
|---|---|---|---|
| 날짜Date | 2023-11-14 ~ 2023-11-14 | 시간Time | 17:00 ~ 18:00 |
| 소속Affiliation | (Keio University, Japan) | 초청자Host | |
| 소개 및 안내사항Content | Title : Lie Group updates for Learning Distributions on Machine Learning Parameters speaker : Eren Mehmet Kıral (Keio University, Japan) abstract : I will talk about our recent paper https://arxiv.org/abs/2303.04397 with Thomas Möllenhoff and Emtiyaz Khan, and other related results. Bayesian Learning learns a distribution over the model parameters, allowing for different descriptions of the same data. This is (contrary to classical learning which "bets-it-all" on a single set of parameters in describing a given dataset and making predictions. We focus on classes of distributions which have a transitive Lie group action on them given by pushforwards of an action on the parameter space. I will also specialize to a few concrete Lie groups and show distinct learning behavior. link : https://us06web.zoom.us/j/6888961076?pwd=ejYxN05jNmhUa25PU2JzSUJvQ1haQT09 |
||
| 성명Field | MINDS Seminar on Machine Learning | ||
|---|---|---|---|
| 날짜Date | 2023-11-14 ~ 2023-11-14 | 시간Time | 17:00 ~ 18:00 |
| 호실Host | 인원수Affiliation | Eren Mehmet Kıral | |
| 사용목적Affiliation | 신청방식Host | (Keio University, Japan) | |
| 소개 및 안내사항Content | Title : Lie Group updates for Learning Distributions on Machine Learning Parameters speaker : Eren Mehmet Kıral (Keio University, Japan) abstract : I will talk about our recent paper https://arxiv.org/abs/2303.04397 with Thomas Möllenhoff and Emtiyaz Khan, and other related results. Bayesian Learning learns a distribution over the model parameters, allowing for different descriptions of the same data. This is (contrary to classical learning which "bets-it-all" on a single set of parameters in describing a given dataset and making predictions. We focus on classes of distributions which have a transitive Lie group action on them given by pushforwards of an action on the parameter space. I will also specialize to a few concrete Lie groups and show distinct learning behavior. link : https://us06web.zoom.us/j/6888961076?pwd=ejYxN05jNmhUa25PU2JzSUJvQ1haQT09 |
||
Admin
·
2023-10-23 10:46 ·
조회 65 
