- ML on Time-series Data/Serving with TensorFlow + 4 Lightning Talks
Allô ML community! Join us for a reboot of this meetup group and the first meetup of 2019. We have a main presentation and 4 lightning talks. Tentative schedule: 18h15-18h30: arrival/registration 18h15-18h45: soft drinks/snacks & networking 18h45-19h30: main presentation/tutorial 19h30-19h45: break 19h45-21h00: announcements and lightning talks 21h00-21h30: networking/casual brainstorming Mandatory registration: https://goo.gl/forms/u7dbnXHT6xwzemJJ3 On the program: - Main presentation by Masood Krohy (Title: Seq2seq Model on Time-series Data: Training and Serving with TensorFlow) - Lightning talks: ~ Jules Lambert (Title: Tutorial on Lime model explanation) ~ Jenny Midwinter (Title: CNN Based Auto-Pilot for a Wheelchair) ~ Grant McKenzie (Title: A machine learning approach to identifying urban neighborhood names) ~ Freddy Lecue (Title: On the importance of explanation for AI adoption in industry) Summaries of talks and bios of presenters: https://www.montrealml.dev/meetup-agenda-april-9th-2019 Important notes - please read in full: RSVP on this site, then confirm with form submission: after a Yes RSVP to temporarily reserve your seat, you have 24 hours to fill and send the above registration form; if not received within the delay, your RSVP may be changed to No (and your seat may be given automatically to the next in line). We use the responses to the above registration form to sign you in at the entry. This meetup group is used to facilitate networking between attendees. Complete profile advantage: meetup group members with names and introduction section properly filled out in their profiles will have priority in attending the meetup in case of limited capacity. Common important details posted at https://www.montrealml.dev/terms : - Overbooking: this is a free-to-attend event and, as such, there is some overbooking. More details are at the above URL - Photo/Video permission - Attendee selection process (in case of limited capacity)
- MTL Machine Learning: Hiver 2017 Winter Meetup
1. Challenges of building AI-powered chatbots that yield business value Erdem Özcan, Head of Research @ Automat Chatbots are at the intersection of messaging and artificial intelligence. Combining these two trends to build solutions that yield real business value is way more challenging than simply plugging together messaging platforms with natural language understanding APIs. In this talk, Erdem will share some of these challenges and the lessons they have learned during Automat's journey. 2. Highlights from the NIPS conference Nicolas Chapados, Chief Science Officer @ Element AI NIPS (Neural Information Processing Systems) is the flagship conference in the areas of learning algorithms and neural computation. Nicolas will present some of the most interesting new research results and insights that surfaced during the most recent edition of this conference. 3. Lightning Community Announcements Do you have a short announcement of relevance to the local Machine Learning community to make? Send an email to seb -at - elementai.com. 4. Conversations: Recent Breakthroughs 2016 was an exciting year for Machine Learning. Let’s gather in smaller groups, unconference-style, and together talk about some of the exciting results that have recently come to the fore. Discussion leaders will each introduce a topic and facilitate a conversation around the techniques and the promising directions they opened. • Libratus (https://arxiv.org/abs/1701.01724) made history by defeating four of the world’s best professional poker players in a 20-day poker competition at Rivers Casino in Pittsburgh. • AlphaGo (https://www.theatlantic.com/technology/archive/2016/03/the-invisible-opponent/475611/) beat Lee Sedol, a Go world champion, 4-1 last March. • Wavenets (https://www.youtube.com/watch?v=CqFIVCD1WWo) generate speech which mimics human voice and sounds more natural than the best existing Text-to-Speech systems. • Image Super-Resolution through Deep Learning (https://github.com/david-gpu/srez) turns images into higher-resolution versions of themselves with plausible sharp features. • The phased LSTM network (https://arxiv.org/abs/1610.09513) adds a time gate to achieve faster convergence than a regular long short-term memory (LSTM) network on tasks which require learning of long sequences. • LipNet (https://www.technologyreview.com/s/602949/ai-has-beaten-humans-at-lip-reading/) was able to identify 93% percent of words correctly from clips of people reading three-second sentences. Human lip-reading volunteers asked to perform the same tasks identified just 52%. • Artistic Style Transfer for Videos (https://www.youtube.com/watch?v=Uxax5EKg0zA) builds on style transfer for images: given an input video and a reference image, it creates a video that imitates the style of the reference image with the content of the input video. • Deep Q-learning (https://www.youtube.com/watch?v=V1eYniJ0Rnk) plays Atari games and improves itself to a superhuman level. • StackGAN (https://www.youtube.com/watch?v=rAbhypxs1qQ) synthesizes high resolution photo-realistic images from text descriptions. Speaker Bios Erdem Özcan is Co-founder and Head of Research of Automat, a seed stage conversational AI startup that is focused on enabling businesses to have personalized, one-on-one conversations with their customers. The cofounders and team collectively have 17 patents in AI and NLP related fields. Automat has received investments from Relay and Real Ventures, the Slackbot fund, USAA and You & Mr. Jones. Their advisory board consists of technology trend spotter Tim O’Reilly, former Chief Creative Officer of TellMe and Nuance Gary Clayton, Richard Socher Chief Scientist at Salesforce, and conversational commerce pioneer Chris Messina. Erdem holds a PhD in Computer Science from Grenoble Institute of Technology and has worked as a researcher in larger companies for more than 10 years. Nicolas Chapados is Chief Science Officer at Element AI, the world’s leading applied research lab in AI. In 2001 he co-founded ApSTAT Technologies, a machine learning technology transfer firm, with his thesis advisor Yoshua Bengio. He also co-founded two spin-off companies: Imagia, to provide AI-based actionable predictive oncology analytics atop medical imaging data, and Chapados Couture Capital, a Quebec-registered quantitative asset manager. He holds a PhD in Computer Science from University of Montreal.
- MTLML: Automne 2016 Fall Meetup
Trip report from the OpenAI unconference Philippe Beaudoin, PhD, VP Research @ Element AI OpenAI, the famous Valley lab funded by Elon Musk, Peter Thiel and others, holds a small invitation-only unconference on Oct 7-8. This talk will present the cool new research areas, insights and vision for the future that were discussed during this unconference. McGill Reasoning & Learning Lab: Recent research overview Ryan Lowe, PhD Candidate, McGill Ryan Lowe will present an overview of the research currently going on in the McGill Reasoning & Learning Lab with a deep dive in some particularly promising topics. IBM Watson AI XPrize intro Sydney Swaine-Simon, District 3 Innovation Quick presentation of the IBM Watson AI XPrize and the ways in which you can contribute. ——————————————————————— About the speakers Philippe Beaudoin Philippe is VP Research at Element AI, a Montreal startup that does research in ML and helps launch spin-offs that tackle the next big challenges in ML and AI. Previously he was a Senior Dev at Google. Philippe holds a PhD from UdeM and did postdoc studies at UBC. Ryan Lowe Ryan is a grad student at McGill University where he does research in Machine learning. He studies recurrent neural networks and reinforcement learning with a particular focus on dialogue systems and language modeling. Sydney Swaine-Simon Sydney is passionate about people and technology innovation which led him to cofound District 3, an innovation center based out of Concordia University and NeuroTechX a non profit building the largest network of Neurotechnology enthusiasts. Currently he spends his free time thinking of new Brain Computer Interfaces to build.
- Social meetup with lightning talks
A Meetup dedicated to Machine Learning and it's applications. We'll start with lightning talks from people who want to share what they're working on. Then, we'll have a panel on "The state of Machine Learning", followed by some time to chat with other folks. In collaboration with: Big Data Montréal (http://www.bigdatamontreal.org/), Montréal Python (http://montrealpython.org/) and MTL Data (http://www.meetup.com/mtldata/). Thanks to Wajam for hosting us this month.