Past Meetup

WiMLDS Montreal #2: International Women's Day!

This Meetup is past

119 people went

Element AI

6650 Rue Saint-Urbain #500 · Montréal, QC

How to find us

Element AI office closest metro station are Beaubien and Parc. 5th floor!

Location image of event venue

Details

We’re excited to announce our second WiMLDS Montreal meetup! The event will coincide with the International Women's Day. Whether you're a data professional or simply curious, you are welcome regardless of your technical level or your gender. The talks will be entirely in English.

=========
Agenda
=========

6:00 pm—Doors open
6:30 pm—Talks
8:30 pm—Networking

=========
Speakers
=========

Negar Rostamzadeh -- Research Scientist at Element AI
Fashion-Gen: The Generative Fashion Dataset and Challenge

Abstract: We introduce Fashion-Gen, a new dataset of 293,008 high definition (1360 x 1360 pixels) fashion images paired with item descriptions provided by professional stylists. Each item is photographed from a variety of angles. We provide baseline results on 1) high-resolution image generation, and 2) image generation conditioned on the given text descriptions for 256 x 256, 3) analyzing the dataset details. We organized a competition at ECCV conference and invited the community to improve upon our baselines.

https://negar-rostamzadeh.github.io

-----
Farzaneh S. Fard -- Ph.D., Machine Learning Scientist at Fluent.ai
Ubiquitous Machine Learning: Lessons from DeepRL in Robotics and Speech

Machine learning algorithms have been used in wide range of applications. In this talk we will target two applications “Robotics” and “Speech recognition” that have been benefit from ML.
In the first part of the talk, “Arbitrated Predictive Actor-Critic” model will be explained that can simulate human target reaching through combining a model-free and a model-based reinforcement learning. The study tests the ability of such a model to control a simulated robotic arm (with two joints) during multiple reaching tasks, including (A) both static and dynamic target properties, (B) absence of visual inputs, (C) adapting to slowly changing kinematics, and (D) the model also shows how arbitration between the two control systems is explainable.
In the second part, some recent techniques and methods that have been used for Speech Recognition as well as some challenges in this field will be mentioned.

https://linkedin.com/in/farzaneh-s-fard
https://twitter.com/FarzanehShfard

-----
Eleonora Vella -- Program Director & Principal Scientist at TandemLaunch Inc.
Diversity & Deep Tech Start-ups

https://www.linkedin.com/in/eleonora-vella-74a03257/
-----
Jihane Lamouri -- Diversity, Equity and Inclusion Advisor at IVADO
Diversity and Knowledge Production

https://www.linkedin.com/in/jihanelamouri/

=========
Follow us
=========

www.twitter.com/WiMLDS_Montreal
www.facebook.com/wimlds.mtl
www.linkedin.com/company/wimlds-mtl
https://medium.com/@WiMLDS_Montreal/