Hong Kong Machine Learning Season 1 Episode 5

 19.12.2018 -  Hong Kong Machine Learning

When? Wednesday, December 19, 2018 from 7:00 PM to 9:00 PM Where? Prime Insight, 3 Lockhart Road, Wan Chai, Hong Kong This meetup was sponsored by Prime Insight which offered the location, drinks and snacks. Thanks to them, and in particular to Romain Haimez and Matthieu Pirouelle. Programme: Nathan Landman Nathan presented his graduate research work at MIT: Abstractive Summarization of Unstructured Text. As usual in these meetups, speakers stay away from the media hype to present the real state of the art, and Nathan was no exception.

Read more… ( ~4 Min.)

Hong Kong Machine Learning Season 1 Episode 4

 21.11.2018 -  Hong Kong Machine Learning

When? Wednesday, November 21, 2018 from 6:30 PM to 8:00 PM Where? WeWork Wan Chai 10F Mass Mutual Tower, 33 Lockhart Road Wanchai Hong Kong Programme: Simon Pavlik Simon did an introductory talk about deep learning techniques applied for natural language processing: CNNs, LSTMs, bi-LSTMs, CRF bi-LSTMs are networks often used to label sentences at the word, or even the character level. His presentation slides.

Read more… ( ~2 Min.)

Hong Kong Machine Learning Season 1 Episode 3

 09.10.2018 -  Hong Kong Machine Learning

When? Tuesday, October 9, 2018 from 6:00 PM to 8:00 PM Where? WeWork Taikoo Wan Rd 21/F, Cityplaza Three 14 Taikoo Wan Road, Taikoo Hong Kong Programme: Mathis Antony Abstract: Making the results of a machine learning project easily reproducible is often no easy feat. We have to work with (or against) OS and language level package managers as well as constantly evolving library APIs and hardware drivers.

Read more… ( ~2 Min.)

Hong Kong Machine Learning Season 1 Episode 2

 21.08.2018 -  Hong Kong Machine Learning

Wilson Fok - Processing Medical 3D Scans - An example of heart segmentation Wilson presented us his approach on the 2018 Atrial Segmentation Challenge based on ensemble of convolutional neural networks. Here are the slides of his talk, and the GitHub for the heart segmentation code. Abstract: Training an ensemble of convolutional neural networks requires much computational resources for a large set of high-resolution medical 3D scans because deep representation requires many parameters and layers.

Read more… ( ~3 Min.)

Hong Kong Machine Learning Season 1 Episode 1

 18.07.2018 -  Hong Kong Machine Learning

Jill-Jênn Vie (https://jilljenn.github.io/) - Mangaki Jill-Jênn presented us his personal project: Mangaki, a non-profit recommender system of manga and anime. From the anime you watched and the manga you read, their algorithm discover new precious pearls that you will love! If you want to join the project, there’s plenty to do! From a technical point of view, Jill-Jênn presented the two main approaches to recommender systems: content-based and collaborative filtering. The approach implemented in Mangaki is a novel one which is both using and mixing the information from content and collaborative filtering.

Read more… ( ~2 Min.)