Past Meetup

TensorFlow and Deep Learning : Dialogue and NLP

This Meetup is past

300 people went


The last few MeetUps have all been pretty 'non-standard' - reporting on the TensorFlow Summit, GoogleIO, etc. This one is back to the standard format, with content more along the lines of our regular "Something for Beginners, Something from the bleeding edge, and Lightning talks" formula.

Planned Talks :

"Machine Learning for Spoken Dialogue Systems" - Matthew Henderson

Matt's background is in statistical methods for conversational language understanding. He leads the Singapore branch of PolyAI, a spin-out from Steve Young's lab at Cambridge University where he did his PhD. PolyAI is building a machine learning platform for spoken dialogue.
After his PhD, he worked on neural network methods for speech synthesis with Heiga Zen at Google Research London, before moving to Ray Kurzweil's language understanding group at Google Research in Mountain View. There he was technical lead for the Smart Reply research team, inventing a new method of modelling email response suggestion that allowed scaling the feature from Inbox to all of GMail. He was the principal data scientist at Carousell, where he launched image caption and category suggestion, chat reply and question answering features. ( )

"Sequence to Sequence Model Advances" - Hardeep Arora

This talk outlines how the way in which Deep Learning can be applied to language processing tasks such as language translation, and how the techniques have quickly evolved over the last few years.

Hardeep is a Principal Director with Accenture’s Finance & Risk Services based in Singapore and is currently Heading the AI/Analytics Center Of Excellence. He has over 18 years experience with financial companies in Asia Pacific region. Outside work he is active on Google’s Kaggle ML platform and is in top 2% of Data Scientist on Kaggle world wide. He holds a MBA Finance from XLRI and a Bachelors Degree in Computer Science.

"The Rise of the Language Model" - Martin Andrews

This talk will explain a major current trend in Natural Language Processing : the increasing focus on using pre-built 'pure' language models (such as ELMO or the model recently announced by OpenAI), and then fine-tuning the output to suit your application. Martin will explain how this works, and you can create better models for your data, leveraging the models created on other, huge datasets by Google / OpenAI / Facebook / etc.


Other talks for this month's event are currently being finalized : If you have something that you'd like to present in a welcoming environment, please let us know by suggesting yourself below...


Talks will start at 7pm (A/V equipment permitting) and end at around 9pm, at which point people normally come up to the front for a bit of a chat with each other, and the speakers.


As always, we're actively looking for more speakers for future events - both '30 minutes long-form', and lightning talks. For the lightning talks, we welcome folks to come and talk about something cool they've done with TensorFlow and/or Deep Learning for 5-10mins (so, if you have slides, then #max=10). We believe that the key ingredient for the success of a Lightning Talk is simply the cool/interesting factor. It doesn't matter whether you're an expert or and enthusiastic beginner: Given the responses we have had, we're sure there are lots of people who would be interested to hear what you've been playing with. Please suggest yourself here :