Tuesday 13 October 2020

A talk on META - LEARNING A Roadmap for Few-Shot Transfer Learning by Dr. Hugo Larochelle, the lead of the Montreal Google Brain team.

A talk on META - LEARNING A Roadmap for Few-Shot Transfer Learning by Dr. Hugo Larochelle, the lead of the Montreal Google Brain team, RBCDSAI, II

 A talk on META - LEARNING  A Roadmap for Few-Shot  Transfer Learning by Dr. Hugo Larochelle, the lead of the Montreal Google Brain team.



Dear All,

 

Greetings from RBCDSAI, IITM !


It gives us immense pleasure in inviting you to the Second RBCDSAI Latentview Colloquium  on October 15, 2020.

A talk on META - LEARNING  A Roadmap for Few-Shot  Transfer Learning by 

Dr. Hugo Larochelle, the lead of the Montreal Google Brain team.  


Registration link:  https://forms.gle/FRa3XsQcj1xYb9Yu8

Time:     6 pm to 7.30 pm 

Date:     15-10-2020, Thursday

Venue:  Online (link will be sent to registered participants)

The registration is open till Oct 15th , 2020  (10.30 am IST )   


More details

 

Abstract:

A lot of the recent progress on many AI tasks were enabled in part by the availability of large quantities of labeled data for deep learning. Yet, humans are able to learn new concepts or tasks from as little as a handful of examples. Meta-learning has been a promising framework for addressing the problem of generalizing from small amounts of data, known as few-shot learning. In this talk, I’ll present an overview of the state of this research area. I’ll describe Meta-Dataset, a new benchmark we developed to push further the development of few-shot learning methods towards a more realistic multi-domain setting. Notably, I’ll present the Universal Representation Transformer (URT) layer, that meta-learns to leverage universal multi-domain features for few-shot classification by dynamically re-weighting and composing the most appropriate domain-specific representations. The URT layer allows us to reach state-of-the-art performance on Meta-Dataset. I’ll end by discussing my perspective on promising future directions.

Bio:

Hugo Larochelle is a Research Scientist at Google Brain and lead of the Montreal Google Brain team. He is also a member of Yoshua Bengio’s Mila and an Adjunct Professor at the Université de Montréal. Previously, he was an Associate Professor at the University of Sherbrooke. Larochelle also co-founded Whetlab, which was acquired in 2015 by Twitter, where he then worked as a Research Scientist in the Twitter Cortex group. From 2009 to 2011, he was also a member of the machine learning group at the University of Toronto, as a postdoctoral fellow under the supervision of Geoffrey Hinton. He obtained his Ph.D. at the Université de Montréal, under the supervision of Yoshua Bengio. Finally, he has a popular online course on deep learning and neural networks, freely accessible on YouTube.  


Aryabhatt Science

Author & Editor

For Science communication

6 comments:

  1. Ranking for the 'Big' keywords, such as 'Plumber Bristol' became less important, as internet users became more savvy with their searches. 'Long tail keywords', and as many as possible, started to grow website visitors and more importantly, conversions. Zoekmachine optimalisatie

    ReplyDelete
  2. You learn faster, and you will be able to find out what works and what does not in your particular line of work. Even your mistakes cannot be considered as failures if you learn from them and use that knowledge to better yourself. Webdesign

    ReplyDelete
  3. Successful non-profit organizations use the Internet to market charitable program. Lead generation

    ReplyDelete
  4. You must always show that the products and services you offer are solutions to a problem, not just tools you use to squeeze money out from customers. Webdesign Antwerpen

    ReplyDelete
  5. In what seems to be a determined move to grow their businesses, most SEOs (82%) are willing to recruit more staff members so as to realize their desired levels of growth. Webdesign

    ReplyDelete
  6. Also there are some restrictions that make communication with the buyer a little difficult, and they don't offer bank wire withdraw - which I like to use. Their fee is 18%, one more reason for me not to use it to much. www.sempris.be/webdesign

    ReplyDelete