I Am AI

I am a Visionary, a Healer, a Creator, and so much more. Through a convergence of technology leaps, social transformations, and genuine economic needs, AI is moving from its academic roots to the forefront of business and industry.

Realized With AI

Preventing disease. Building smart cities. Revolutionizing analytics. These are just a few things happening today with AI and, specifically, deep learning. Today, it’s empowering organizations to transform moonshots into real results.

The Faces of AI

Learn what fuels the elite thinkers of today. This series spotlights the rising stars of AI in “their own words.” From childhood dreams to recent accomplishments, they give you an inside look at what motivates them to do their best work.

Deep Learning Meetup

The aim of this meetup is to bring together people interested in the family of machine learning methods that are concerned with learning distributed, hierarchical ("deep") representations.The format will be based around guest speakers sharing new research ideas and applications covering a wide range of fields from computer vision and natural language processing to autonomous systems and prognostics.Entrepreneurs, working professionals, students, academicians, investors, and just about anyone who is interested in Deep Learning is invited.This Meetup will serve to be an open platform for people to share knowledge, practices, research, applications and critiques of deep learning.If interested, Register now.

Present Speakers

Shreyas Sharma Machine Learning Research Intern at Samsung Research

ALL ABOUT SELF-DRIVING CARS


This talk will provide the necessary background for understanding the different tasks and associated challenges with autonomous vehicles, the different sensors and data sources one can use, and the architecture of Autonomous Driving stack. We will take a look at the popular deep learning solutions used while also touching upon the robotics aspect using ROS.

Register Here

Sergio Garrido Machine Learning Research Intern at Amazon

DEEP GENERATIVE MODELS FOR TABULAR DATA


We will motivate the generation of tabular data (agents) through deep generative models. We will review deep generative models and their relation with neural networks and bayesian inference. I will introduce a way to measure the quality of the generated agents and provide some results of two common deep generative models.

Register Here

Ruslan Martimov PhD, Senior Machine Learning Engineer at VK.com

AUTOMATIC CONTENT RECOGNITION: DO SOUNDS MATTER?


Automatic content recognition (ACR) is an identification technology to recognize content played on a media device or present in a media file" (Wikipedia). I’m going to propose a framework for automatic audio content recognition that is based on deep learning networks and the Facebook Faiss library. I will go over experimental results for different types of audio content and share lessons that I’ve learned along the way.

Register Here

Eliya NachmaniPhD, Facebook AI Research

SEPARATION OF MIXED AUDIO SEQUENCE

I'll present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art for various scenarios – noisy and reverberant environment. Furthermore, the method achieves state of the art performance for music source separation

Register Here

Gianluca DetommasoMachine Learning Scientist at Amazon

FINDING CERTAINTY IN UNCERTAINTY: A UNIFIED PERSPECTIVE ON VARIATIONAL INFERENCE, NORMALIZING FLOW AND TRANSPORT MAPS


So many algorithms, so many names, so many differences. In this talk, I will swim against the tide and rather highlight some of the common roots among popular machine learning methods to estimate uncertainty. Perhaps obvious perhaps uncanny, we will see how variational inference, normalizing flow and transport maps can all be described under a simple unified perspective

Register Here

Danya Chapenko Data Science, Yahoo Japan

REINFORCEMENT LEARNING IN RECOMMENDER SYSTEMS


An introduction into Recommender Systems and Reinforcement learning domain Applications of Reinforcement Learning in Recommender Systems. How can we optimize long-term satisfaction? Challenges in production-ready solutions.

Register Here