7th CODH Seminar
Manifold Mixup: Encouraging Meaningful On-Manifold Interpolation as a Regularizer

Theme

We organize a talk about deep networks by Alex Lamb, who is a PhD student at the University of Montreal with Yoshua Bengio and Aaron Courville. Anyone is welcome to join the seminar.

Basic Information

Title Manifold Mixup: Encouraging Meaningful On-Manifold Interpolation as a Regularizer
Speaker Alex Lamb
Date 15:00-16:00, July 31 (Tue), 2018
Venue 1901 Meeting Room, National Institute of Informatics
Participation Anyone is welome to join. Free of charge. Registration is not required, but if you are from the outside of NII, you can make a contact with kitamoto @ nii.ac.jp about how to enter the building. Access to NII.
Presentation Manifold Mixup (Google Slides)
Abstract Deep networks often perform well on the data manifold on which they are trained, yet give incorrect (and often very confident) answers when evaluated on points from off of the training distribution. This is exemplified by the adversarial examples phenomenon but can also be seen in terms of model generalization and domain shift. We propose Manifold Mixup which encourages the network to produce more reasonable and less confident predictions at points with combinations of attributes not seen in the training set. This is accomplished by training on convex combinations of the hidden state representations of data samples. Using this method, we demonstrate improved semi-supervised learning, learning with limited labeled data, and robustness to adversarial examples. Manifold Mixup requires no (significant) additional computation. Analytical experiments on both real data and synthetic data directly support our hypothesis for why the Manifold Mixup method improves results.
Bio Alex Lamb is a PhD student at the University of Montreal with Yoshua Bengio and Aaron Courville. He is interested in making deep learning more robust, general, and useful in realistic learning scenarios. Previously he worked on the demand forecasting group at Amazon and did his undergraduate at the Johns Hopkins University. He also creates machine learning tutorials and guides on his youtube channel: https://www.youtube.com/c/TheNuttyNetterAlexLamb

Past CODH Seminars

2024-06-06

22th CODH Seminar - Hentaigana in the Digital Age: The Inheritance and New Developments of the Japanese Written Character Culture

2024-03-04

21th CODH Seminar - Digital History: Concepts and Practices

2023-02-27

20th CODH Seminar - The end of lexicography, welcome to the machine: On how ChatGPT can already take over all of the dictionary maker's tasks

2023-03-01

19th CODH Seminar - Collective Intelligence and Creative AI: A framework for augmenting creative human expression

2023-01-22

18th CODH Seminar - Micro Typology and Digital Archive: Case Studies on Bantu languages and Japanese-Ryukyuan languages

2022-07-01

DH 2022 Tokyo Commemorative Lecture Series / 17th CODH Seminar - Historical Big Data - THE DARK MATTER OF HISTORY

2022-03-28

16th CODH Seminar - Digital Archives for Cities and Towns - Historical Big Data and Usage in the Real World

2021-07-29

15th CODH Seminar - Art History Research to be Transformed by IIIF and AI - Interpreting Japanese Painting Scrolls in Middle Ages by Style Comparative Study on Large-Scale Facial Expression Data

2021-02-18

14th CODH Seminar - 100 Recipes for IIIF Curation Platform

2021-01-22

13th CODH Seminar - Present and Future of Historical Big Data Research

2020-08-05

12th CODH Seminar (Online) - AI for Culture: From Japanese Art to Anime

2020-02-21

12th CODH Seminar - AI for Culture: From Japanese Art to Anime

2019-09-25

11th CODH Seminar - Text Mining for Analyzing Research Communities: Sociological Topics and Socio-Technical Imaginaries

2019-03-11

10th CODH Seminar - Document Analysis and Character Recognition

2019-01-08

9th CODH Seminar - Computer Vision with Limited Labeled Data

2018-11-22

8th CODH Seminar - Exploring Deep Learning for Classical Japanese Literature, Machine Creativity, and Recurrent World Models!

2018-07-31

7th CODH Seminar - Manifold Mixup: Encouraging Meaningful On-Manifold Interpolation as a Regularizer

2018-03-12

6th CODH Seminar - Historical Big Data - Challenges in Transforming Historical Documents to Structured Data for the Integrated Analysis of Records in the Past -

2017-12-04

5th CODH Seminar - Trustworthy Data Repositories - Forum for Sharing Practical Information about CoreTrustSeal Certification -

2017-07-27

4th CODH Seminar - A New Trend on Image Delivery in Digital Archives - IIIF's Potential for Standardization and Sophistication of Image Access -

2017-05-30

3rd CODH Seminar - Usage of DOI for Humanities - Assignment of DOI for Scholarly Resources such as Research Data and Museum Collections -

2017-02-10

2nd CODH Seminar - Old Japanese Character Challenge - Future of Machine Recognition and Human Transcription -

2017-01-23

1st CODH Seminar - Big Data and Digital Humanities