h1

Visiting Zhengzhou University

September 27, 2019
Workshop at Zhengzhou, 2019

Faculty and some students after the workshop, 27/09/19.

Dr. Ming Liu of Deakin organised for Dr. Lan Du and I to give a series of lectures on machine learning and natural language processing at Zhengzhou University in Henan province, from 25-27th September.   I gave versions of some previous talks, as well as presenting a new talk on some of the fundamental principles behind some of the new techniques in deep neural networks like pre-training.

The photo above shows me, with Lan and Ming on my left and Prof. Zan, our principal host, on the right.  Several other Zhengzhou faculty are in the front row and some of the masters + phd students in the back row.   Zhengzhou is a large university with the best students in Henan.  The food was, of course, fabulous.  We had a small dinner with the Dean of the entire Engineering Faculty (seen cut-off, on far left), no less, on Monday night, and I was introduced to the toasting customs of Henan with their tiny 10ml shot glasses!

Dinner at Zhengzhou University

At the faculty club 25/09/19, with the Dean on the far left.  Lan is having his soup and Ming is waving.

h1

Kicking off DARPA LwLL project

August 14, 2019

Reza Haffari put together a team and we won a bid in the DARPA Learning with Less Labels (LwLL) programme.  The picture below shows us all on 14th August discussing plans prior to flying off to Arlington, Virginia, to take part in the starting workshop.  Our team comprises the 5 smiling academics below as well as Prof. Anton ven den Hengel of University of Adelaide.  Reza, Dinh and I made the long haul to Arlington for 26-27th August 2019, where we met some really smart folks in the other teams!

Monash LwLL team

The Monash DARPA LwLL team: Reza, Xiaojun, Dinh, Geoff and Wray

h1

Turning Point and Monash at Google

July 31, 2019

Turning Point colleague, Sam Campbell, and I went to the Google AI Impact Challenge Accelerator event in London on 29th-31st July (see the video here, I get a brief shots at 0:14 and 0:20 and Sam gets an interview at 0:49).  It was an in depth technology review so we could help design our system.  We had a number of very clued-in Google experts supporting us in designing our architecture.  My systems and internet applications experience is over 20 years old, so I get the general ideas but don’t know the modern specifics!

Lots the of AI Impact folks from Google attended and we all agreed the committment and support from Google was fabulous.  We’re in the top right, with Sam holding the “Turning Point” sign, me below him.

AI Impact Challenge Accelerator Tech Sprint

All the teams at the London tech event, 31/07/19.

h1

Southeast Asia Machine Learning School

July 9, 2019

Very fortunate to be asked to give a lecture on “Foundations of Supervised Learning” at SEA-MLS in Jakarta on 8th July.  The school was co-organised by Google, so opening talk by Google and a member of the Indonesian government.  A big crowd too!  Everyones slides are up on the schedule page.

Never been to Jakarta so an exciting opportunity meet some colleagues, some students, in a lovely environment. Monash has a school at Malaysia so a few Malaysia Monash folks turned up too.  Here we are after my lecture.

SEAMLS-Monash2

Monash Malaysia and Melbourne students at SEA-MLS.

h1

AI suicide surveillance with Turning Point

June 23, 2019
Wray-Dan-Debbie-Lauchpad

Wray, Dan and Debbie at Google Launchpad, 15/05/2019

Along with Prof. Dan Lubman’s team at Turning Point, and funded through Google’s innovative AI for Social Good programme, I’ll be developing an AI system to accelerate “coding” (a form of content analysis) of ambulance records so we can understand the nature of suicide in Australia.   The local press has it so:

Google taps local addiction service to build AI suicide surveillance system

As the Google blurb says:

By using AI tools to analyze these records, Turning Point, a national center within Eastern Health, will uncover critical suicide trends and potential points of intervention to better inform policy and public health responses.

For us researchers, it means unifying a bunch technologies that I’ve been working in for a while like active learning, multi-label classification, multi-task learning and crowd-sourcing.  But most importantly, all these need to be placed in the context of​ doing accurate and properly monitored coding while at the same time trying to minimise costly expert (human) effort.  This is important stuff for NGOs and health organisations so we’re really excited by the application opportunities this can give us all.

In mid May Dan Lubman, Debbie Scott and I flew off to Google’s Lauchpad Space in San Francisco to spend a week with other members of the programme for a bootcamp, to brainstorm about our project and get coaching from Google’s experts.  Google has a lot of other plans for us to, in terms of supporting the development, which we are very grateful for!

h1

Visiting Helsinki

December 21, 2018

Visited my old workplace, University of Helsinki, where I visited various faculty like Prof. Petri Myllymaki, Teemu Roos, Arto Klami and others. Across the bay is Aalto University with folks like Prof. Sami Kaski.   The machine learning groups in broader Helsinki are very strong, with loads of researchers, quality students, and a very vigorous start-up and high-tech culture.

Gave a talk at Machine Learning Coffee Seminar on 17/12 (which serves porridge as well as coffee), and attended the AI Day on 12/12. The AI Day is organised by the recently convened Finnish Centre for Artifical Intelligence, and the speakers were senior researchers from Finland describing their broader vision and direction, so really interesting stuff and very educational. Lots of creativity in there, for instance combining simulation, machine learning, HCI and cognitive psychology.

h1

Invited talk at ACML in Beijing

October 11, 2018

I’ve given an invited talk at ACML in Beijing November:  see Invited Speakers at the ACML website.

Wray's talk at ACML 2018

I talked about the state of Machine Learning, contrasting the old with the new, and discuss where we may head next.  Moreover, I gave some warnings about some problems we are currently facing.  PDF slides for the talk are here.  Abstract is given below.  Prof. Jun Zhu (Tsinghua U.) has had some similar ideas so we conferred afterwards.

Several of us from Monash went:  in the picture are Ye Zhu, Wray Buntine, Lan Du, Yuan Jin and He Zhao.Monash (past and present) at ACML 2018

Something Old, Something New, Something Borrowed, Something Blue

Something Old: In this talk I will first describe some of our recent work with hierarchical probabilistic models that are not deep neural networks. Nevertheless, these are currently among the state of the art in classification and in topic modelling: k-dependence Bayesian networks and hierarchical topic models, respectively, and both are deep models in a different sense. These represent some of the leading edge machine learning technology prior to the advent of deep neural networks. Something New: On deep neural networks, I will describe as a point of comparison some of the state of the art applications I am familiar with: multi-task learning, document classification, and learning to learn. These build on the RNNs widely used in semi-structured learning. The old and the new are remarkably different. So what are the new capabilities deep neural networks have yielded? Do we even need the old technology? What can we do next? Something Borrowed: to complete the story, I’ll introduce some efforts to combine the two approaches, borrowing from earlier work in statistics.