We're excited to welcome Alex Lamb for a talk on "Generators, Manifolds, and Adversarial Mixup Resynthesis" at the University of Tokyo.
A motivating idea behind deep learning is that a model can learn to map from the high-dimensional space of observations unto a low-dimensional space of salient explanatory factors which vary across the data. Generative models with latent variables perhaps embody this idea most closely. In this talk we'll explore the relationship between deep models and manifolds, trying to make the relationship more explicit and rigorous. At the same time we'll discuss a recent paper, "Adversarial Mixup Resynthesis", that takes a new perspective on latent variables in generative models.
● 7:00pm Doors open
● 7:30pm – 8:20pm "Generators, Manifolds, and Adversarial Mixup Resynthesis", Alex Lamb
● 8:20pm – 8:45pm Q&A
● 8:45pm – 9:00pm Closing
–– SPEAKER BIO ––
Alex Lamb grew up in Western Maryland and did his undergraduate at Johns Hopkins University. Afterwards he worked on new forecasting algorithms and systems at Amazon for a few years. Now he's a PhD student at the Montreal Institute for Learning Algorithms (MILA) in Yoshua Bengio's lab, and enjoys working on new algorithms for deep learning. On the side he also enjoys working on medieval Japanese document recognition. http://alexmlamb.github.io/
💙 –– THANK YOU ––
A big Thank You goes out to the University of Tokyo and Michael Fabinger for hosting this event. http://www.cirje.e.u-tokyo.ac.jp/research/workshops/stateng/stateng.html
–– MLT PATRON ––
Become a MLT Patron and help us to keep MLT meetups like this inclusive and for free. https://www.patreon.com/MLTOKYO
–– SUBSCRIBE ––
Subscribe to our monthly newsletter: https://mltokyo.ai/membership-join
–– FIND MLT RESOURCES ––
–– RECRUITING ––
MLT events are for community building and knowledge sharing. We politely ask that company representatives, recruiters and consultants looking to hire or sell their services do not come to this event.
–– CODE OF CONDUCT ––
MLT promotes an inclusive environment that values integrity, openness and respect. https://github.com/Machine-Learning-Tokyo/MLT_starterkit