Sydney Machine Learning, Tues, 4th of Sep @ Microsoft

Microsoft will be our host for this Sydney Machine Learning meetup at Cliftons (Level 3, 10 Spring St) in Sydney CBD.

Come along for beer, pizza, networking and talks from Matt Gibson, Ph.D. student working in computer vision at UNSW’s machine learning group, Kosuke Fujimoto from Microsoft’s Tokyo based Machine Learning group & Krit Kamtuo Software Engineer at Microsoft APAC for Machine Vision focused talks.

First Presentation Summary:

Title: Learning with not quite the right labels

Summary:

Having the right data is often as important as having the right model for building effective computer vision systems. Even if you have enough data, what do you do when don't have the right labels? Common problems arising in image understanding include only having partially labelled data, have the wrong type of labels and noisy labels. Broadly these problems can be addressed by an area of research called weakly supervised learning. I will give an overview of some strategies coming from weakly supervised learning to help train good predictive models in the presence of these difficulties. The tools used will include ConvNets combined with some interesting applications of familiar friends such as the EM algorithm and graph-based clustering.

Matt Gibson is a Ph.D. student working in computer vision and machine learning at UNSW. He is interested in building high performance machine learning systems for visual understanding.

Second Presentation Summary:

Title: How can we innovate our workstyle at construction sites with Image Classification?

Kosuke, Takenaka Corporation is one of the top 5 largest construction companies in Japan. Their site supervisors perform site visits, record the progress of ongoing construction as well as assign appropriate resourcing from their workforce by writing up the report every evening. This involves taking a lot of photos and organizing them based on the construction progress.

In this talk, I walk you through an effort by Takenaka with help from Microsoft to automatically organize photos utilizing Keras and Transfer Learning to make workstyle innovation at construction sites possible.

Third Presentation Summary:

Title : Using Batch AI to train NLP based on TensorFlow and CNTK in the retail industry

Summary:

Currently, SSG.COM, the subsidiary of Shinsegae Group the largest retailer in South Korea, is developing an AI chatbot service based on deep learning. It was decided that the internet as as service-based architecture is not efficient because it requires additional resources if the operation production scale is increased.

We will discuss why the AI model training layer does not have to be running at all times but the GPU-supported VM should be used continuously, to reduce costs to SSG.COM.

Openhack

This meetup is a collaboration with Microsoft’s Openhack which will be happening from the 4th to the 6th of September. For more info, you can find more about it here:

https://www.microsoftevents.com/profile/form/index.cfm?PKformID=0x43738390001

Time: 6:00 – 8:30 pm

Venue:

cliftons, level 3, 10 spring street sydney

Schedule:

18:00 -18:30 – dinner, drinks & network

18:30 – 19:05 – Matt Gibson’s talk

19:05– 19:15 – break

19:15 – 20:00 – Kosuke & Krit’s talks.