multimodal model agnostic meta learning via task aware
play

Multimodal Model Agnostic Meta-Learning via Task-Aware Modulation - PowerPoint PPT Presentation

Oct 09, 2023 •310 likes •509 views

05:00 -- 07:00 PM @ East Exhibition Hall B + C #31 Multimodal Model Agnostic Meta-Learning via Task-Aware Modulation Risto Vuorio* Shao-Hua Sun* Hexiang Hu Joseph J. Lim Data Sample Ground Truth Data Sample Ground Truth Data Sample

  1. 05:00 -- 07:00 PM @ East Exhibition Hall B + C #31 Multimodal Model Agnostic Meta-Learning via Task-Aware Modulation Risto Vuorio* Shao-Hua Sun* Hexiang Hu Joseph J. Lim

  3. Data Sample Ground Truth

  4. Data Sample Ground Truth

  5. Data Sample Ground Truth

  6. θ Data Sample Ground Truth MAML

  7. Sinusoid Absolute Value Data Sample Ground Truth Tanh

  8. Sinusoid Absolute Value Data Sample Ground Truth Tanh

  9. Sinusoid Absolute Value θ Data Sample Ground Truth MAML (1-mode) Tanh

  10. Sinusoid Absolute θ 1 θ 3 Value θ 2 Data Sample Ground Truth MAML (1-mode) MAML (3-mode) Tanh

  11. x Task Network y ˆ y

  12. ( ( x Samples × K y x Modulation Task Network Network y ˆ y

  13. Evaluations: Regression

  14. Evaluations: Regression

  15. Evaluations: Reinforcement Learning ProMP Ours

  16. Evaluations: Classification (a) Omniglot (b) Mini-ImageNet (c) FC100 (d) CUB (e) Aircraft

  17. Evaluations: Classification (a) Omniglot (b) Mini-ImageNet (c) FC100 (d) CUB (e) Aircraft

  18. 05:00 -- 07:00 PM @ East Exhibition Hall B + C #31 Multimodal Model Agnostic Meta-Learning via Task-Aware Modulation Risto Vuorio* Shao-Hua Sun* Hexiang Hu Joseph J. Lim

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Bayesian Model-Agnostic Meta-Learning Taesup Kim* (presenter), Jaesik Yoon* Ousmane Dia,

Bayesian Model-Agnostic Meta-Learning Taesup Kim* (presenter), Jaesik Yoon* Ousmane Dia,

Bayesian Model-Agnostic Meta-Learning Taesup Kim* (presenter), Jaesik Yoon* Ousmane Dia, Sungwoong Kim, Yoshua Bengio, Sungjin Ahn Model-Agnostic Meta-learning (MAML) gradient-based meta-learning framework meta-update task adaptation

886 views • 22 slides
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks Chelsea Finn, Pieter Abbeel,

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks Chelsea Finn, Pieter Abbeel,

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks Chelsea Finn, Pieter Abbeel, Sergey Levine Presented by: Teymur Azayev CTU in Prague 17 January 2019 Deep Learning Very powerful, expressive differentiable models.

579 views • 18 slides
Model-Agnostic Meta-Learning Universality, Inductive Bias, and Weak Supervision Chelsea Finn

Model-Agnostic Meta-Learning Universality, Inductive Bias, and Weak Supervision Chelsea Finn

Model-Agnostic Meta-Learning Universality, Inductive Bias, and Weak Supervision Chelsea Finn Why Learn to Learn? - e ff ectively reuse data on other tasks - replace manual engineering of architecture, hyperparameters, etc. - learn to quickly

915 views • 30 slides
Learning Task-Agnostic Embedding of Multiple Black-Box Experts for Multi-Task Model Fusion Nghia

Learning Task-Agnostic Embedding of Multiple Black-Box Experts for Multi-Task Model Fusion Nghia

Learning Task-Agnostic Embedding of Multiple Black-Box Experts for Multi-Task Model Fusion Nghia Hoang (MIT-IBM Watson AI Lab), Thanh Lam (National University of Singapore), Bryan Kian Hsiang Low (National University of Singapore), Patrick Jaillet

521 views • 24 slides
Task-Agnostic Dynamics Priors for Deep Reinforcement Learning Yilun Du 1 , Karthik Narasimhan 2

Task-Agnostic Dynamics Priors for Deep Reinforcement Learning Yilun Du 1 , Karthik Narasimhan 2

Task-Agnostic Dynamics Priors for Deep Reinforcement Learning Yilun Du 1 , Karthik Narasimhan 2 1 MIT, 2 Princeton Key Questions t t+1 Can we learn physics in a task-agnostic fashion? Does it help sample efficiency of RL? Can we

555 views • 14 slides
Meta Reinforcement Learning as Task Inference Jan Humplik, Alexandre Galashov, Leonard

Meta Reinforcement Learning as Task Inference Jan Humplik, Alexandre Galashov, Leonard

Meta Reinforcement Learning as Task Inference Jan Humplik, Alexandre Galashov, Leonard Hasenclever, Pedro A.Ortega, Yee Whye Teh, Nicholas Heess Topic: Bayesian RL Presenter: Ram Ananth Why meta Reinforcement Learning? First Wave of Deep

912 views • 63 slides
Task-agnostic priors for reinforcement learning Karthik Narasimhan Princeton Collaborators:

Task-agnostic priors for reinforcement learning Karthik Narasimhan Princeton Collaborators:

Task-agnostic priors for reinforcement learning Karthik Narasimhan Princeton Collaborators: Yilun Du (MIT), Regina Barzilay (MIT), Tommi Jaakkola (MIT) State of RL ~1100 PF/s days ~800 PF/s days or 45000 years (source: OpenAI) Little to no

556 views • 30 slides
Task-Agnostic Sample Design for Machine Learning Bhavya Kailkhura CASC, Lawrence Livermore

Task-Agnostic Sample Design for Machine Learning Bhavya Kailkhura CASC, Lawrence Livermore

Task-Agnostic Sample Design for Machine Learning Bhavya Kailkhura CASC, Lawrence Livermore National Lab Joint work with: Jay Thiagarajan, Qunwei Li, Jize Zhang, Yi Zhou, Timo Bremer This work was performed under the auspices of the U.S.

333 views • 10 slides
Meta-transfer Learning for Few-shot Learning Yaoyao Liu Tianjin University and NUS School of

Meta-transfer Learning for Few-shot Learning Yaoyao Liu Tianjin University and NUS School of

NUS-Tsinghua-Southampton Centre for Extreme Search Meta-transfer Learning for Few-shot Learning Yaoyao Liu Tianjin University and NUS School of Computing OUTLINE Research Background Methods Meta-transfer Learning Hard-task

455 views • 33 slides
The Peculiar Optimization and Regularization Challenges in Multi-Task Learning and Meta-Learning

The Peculiar Optimization and Regularization Challenges in Multi-Task Learning and Meta-Learning

The Peculiar Optimization and Regularization Challenges in Multi-Task Learning and Meta-Learning Chelsea Finn Stanford training data test datapoint Braque Cezanne By Braque or Cezanne? How did you accomplish this? Through previous

851 views • 43 slides
Multi-Task & Meta-Learning Basics CS 330 Logistics Homework 1 posted today, due Wednesday,

Multi-Task & Meta-Learning Basics CS 330 Logistics Homework 1 posted today, due Wednesday,

Multi-Task & Meta-Learning Basics CS 330 Logistics Homework 1 posted today, due Wednesday, October 9 Fill out paper preferences by tomorrow. TensorFlow review session tomorrow, 4:30 pm in Gates B03 Plan for Today Multi-Task Learning - Models

917 views • 42 slides
Deep Multi-Task and Meta-Learning CS 330 Course Logistics Information & Resources Chelsea

Deep Multi-Task and Meta-Learning CS 330 Course Logistics Information & Resources Chelsea

Deep Multi-Task and Meta-Learning CS 330 Course Logistics Information & Resources Chelsea Finn Suraj Nair Tianhe (Kevin) Yu Abhishek Sinha Tim Liu Instructor TA TA TA TA Course website : http://web.stanford.edu/class/cs330/ Piazza :

1.17k views • 44 slides
Meta Learning Shengchao Liu Background Meta Learning (AKA Learning to Learn) A

Meta Learning Shengchao Liu Background Meta Learning (AKA Learning to Learn) A

Meta Learning Shengchao Liu Background Meta Learning (AKA Learning to Learn) A fast-learning algorithm: quickly adapted from the source tasks to the target tasks Key terminologies Support Set & Query Set C-Way K-Shot

2k views • 41 slides
Me Meta Lear Learnin ing A Bri Brief Introduct ction Xiachong Feng Ou Outline

Me Meta Lear Learnin ing A Bri Brief Introduct ction Xiachong Feng Ou Outline

Me Meta Lear Learnin ing A Bri Brief Introduct ction Xiachong Feng Ou Outline Introduction to Meta Learning Types of Meta-Learning Models Papers: Optimization as a model for few-shot learning ICLR2017

913 views • 60 slides
One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning Authors: Tianhe Yu*,

One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning Authors: Tianhe Yu*,

One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning Authors: Tianhe Yu*, Chelsea Finn*, Annie Xie, Sudeep Dasari, Tianhao Zhang, Pieter Abbeel, Sergey Levine CS 330: Deep Multi-Task and Meta-Learning October 16, 2019

432 views • 24 slides
Multimodal Machine Learning Louis-Philippe (LP) Morency CMU Multimodal Communication and Machine

Multimodal Machine Learning Louis-Philippe (LP) Morency CMU Multimodal Communication and Machine

Multimodal Machine Learning Louis-Philippe (LP) Morency CMU Multimodal Communication and Machine Learning Laboratory [MultiComp Lab] 1 CMU Course 11-777: Multimodal Machine Learning 2 Lecture Objectives What is Multimodal? Multimodal:

1k views • 72 slides
Air Barrier Expected Air Barrier & Technology First Benefit of an effective air barrier is

Air Barrier Expected Air Barrier & Technology First Benefit of an effective air barrier is

Unit EA3.2 EA3.3 Rin ACH at 50 Airflow LEED SAL 7 History /Type (2pts) (3pts) gTy PA (CFM) for pe HOMES Pts 13/O2 1819 1083 A 3.6 1560 2 Initial Reading before insulation. 13/O2 910 541 B 2.77 600 2 2nd Reading after

304 views • 9 slides
Size distribution of aerosols attached by cosmogenic nuclide Be-7 in the atmosphere at the TA

Size distribution of aerosols attached by cosmogenic nuclide Be-7 in the atmosphere at the TA

Size distribution of aerosols attached by cosmogenic nuclide Be-7 in the atmosphere at the TA telescope station 1 Dept. of Physics, Yamagata University 2 Dept. of Earth and Environmental Sciences, Yamagata University 3 Institute of Cosmic Ray

433 views • 12 slides
2/28/2019 1 2 3 4 When parents attached When parents talked about faith little importance to at

2/28/2019 1 2 3 4 When parents attached When parents talked about faith little importance to at

2/28/2019 1 2 3 4 When parents attached When parents talked about faith little importance to at home, attached great religion, importance to it, and were active in faith, 5 6 1 2/28/2019 Prepare for Celebrate the Live the the Sacrament

509 views • 3 slides
ATLAS Silicon Tracker operation and performance Urban Bitenc Freiburg University on behalf of

ATLAS Silicon Tracker operation and performance Urban Bitenc Freiburg University on behalf of

ATLAS Silicon Tracker operation and performance Urban Bitenc Freiburg University on behalf of the ATLAS SCT Collaboration Vertex 2010 19 th International Workshop on Vertex Detectors 6 th -11 th June 2010, Loch Lomond, Scotland Introduction

557 views • 23 slides
Equipping students with the 21st Century Skills they will need at university Nerilee Hall

Equipping students with the 21st Century Skills they will need at university Nerilee Hall

Equipping students with the 21st Century Skills they will need at university Nerilee Hall International Christian School, Hong Kong halln@ics.edu.hk WELCOME! PLEASE READ ARTICLES ON YOUR TABLE Changing society (knowledge society, ICTs,

803 views • 21 slides
PETS Town Hall 18th Privacy Enhancing Technologies Symposium Rachel Greenstadt Kostas

PETS Town Hall 18th Privacy Enhancing Technologies Symposium Rachel Greenstadt Kostas

PETS Town Hall 18th Privacy Enhancing Technologies Symposium Rachel Greenstadt Kostas Chatzikokolakis (2017-2018) (2019-2020) Damon McCoy Carmela Troncoso (2017-2018) (2018-2019) Logistics Hike Please confirm Bring filled form

455 views • 8 slides
Town Hall FY 19 Meeting Wednesday, February 20, 2019 11:00 am to 12:00 pm Welcome and please

Town Hall FY 19 Meeting Wednesday, February 20, 2019 11:00 am to 12:00 pm Welcome and please

Town Hall FY 19 Meeting Wednesday, February 20, 2019 11:00 am to 12:00 pm Welcome and please stand by we will begin shortly! Ranjna Das, Executive Board President Kathy Schalk-Greene, Executive Director Todays Agenda Board

635 views • 14 slides
Redes de Computadores Aula 19 Aula passada Aula de hoje Topologia de rede Redes sem fio local

Redes de Computadores Aula 19 Aula passada Aula de hoje Topologia de rede Redes sem fio local

Redes de Computadores Aula 19 Aula passada Aula de hoje Topologia de rede Redes sem fio local Problema do Hubs e Switches terminal escondido Wi-Fi (802.11) Figueiredo 2011 Elements of a wireless network wireless hosts laptop,

266 views • 12 slides

More recommend