I recently had the honour of attending the MSF Canada AGM in Montreal to join Ivan Gayton and Stephen Mather (from Open DroneMap fame) run a drone day for the MSF logisticians. The aim being to show the realm of the possible with current drone technology as well as touch on future trends and ethical considerations.
A second agenda we had was to promote the democratisation of drone technology to enable crowd sourced imagery collection as part of the Missing Maps initiative. More specifically, the goal is to bring drone technology down to a level where it can be built, maintained, and operated safely, responsibly, and independently by a local high school in South Sudan, the local University of Lubumbashi, or similar.
The full (draft) concept note behind this can be found here.
Its late and I’m on my way back from the final demo evening of the Advanced Skills Initiative (ASI). The ASI programme takes disgruntled academics and puts them through an intensive 8 week data science course so they can move into the bustling data science job market. I was a mentor on the machine learning front and it was great to see the fellows evolve and battle through their projects.
One thing struck me though. Something that has been bugging me for a while. Projects pitched at events and meetups like this invariably cover product recommendation, preference learning, financial NLP, churn prediction, adclick prediction, social media trending analysis, etc.
As somebody who likes tangible things, I can’t help but wonder. Where are the projects & startups from aerospace, automotive, marine and other engineering disciplines? Why aren’t we seeing projects from Airbus on smart IVHM, from Jaguar on crumple zones, from Reaction Engines on engine performance, from ASV on marine autopilots, from Princess on vibration control, from McLaren on race strategy, from Dyson on path planning, etc. I personally find these things hugely interesting and fascinating topics. The possibilities for data science / machine learning are endless, prognostics being the obvious example.
A short post to share the slides I used during my talk at the 4th PyData London Meetup. Organized by Ian Oszvald, co-Taarifian Florian Rathgeber, and others, its always a full house with a friendly crowd.
Given the limited time I had to put something together I think the talk was well received and triggered lots of good feedback and conversations in the pub afterwards. Hopefully I managed to ‘turn’ a few attendees 🙂
Aside: There has been a lot happening on my end the last couple months and its been tough (but exciting!) keeping up with it all. My digital prescense has been lagging behind somewhat but slowly getting there.
A lot has changed since I last blogged about Taarifa. We have been the recipient of a World Bank Innovation Fund grant and are going through the Geeks Without Bounds Humanitarian Accelerator. Work is really kicking off in earnest now and if you follow the project you will see much happening over the next two months.
In order to improve the platform and grow the community we are running a number hackathons around the world. You are hereby cordially invited to come hack on data, software (front and back end), hardware, and all the bits between in
There’s not much in the way of access to clean water in Tanzania. In the informal settlements, there are a bunch of water points, but many of them are broken. Rather than a continual process of putting in new ones, the local water engineers want to fix the existing ones – but they don’t know where the broken points are. This also prevents large-scale response organizations from accurately deploying resources (and seeing what initiatives are already working).
Update: These courses have now been taught successfully. If you are interested let me know.
Note: These were originally delivered through Persontyle, however I am no longer affiliated with them in any way after a very unprofessional experience.
I am happy to announce I will be teaching two Machine Learning courses over the summer: A one day high level overview of machine learning is all about and a longer 5 day introductory course that goes into more depth and includes lots of hands on labs with Python scikit-learn. See below for details.
Today I attended the CDAC Workshop Digital Humanitarian Response – What Should the Future Look Like?
Organised by Justine McKinnon from Standby Task Force and Jessica Roland from Translators Without Borders, it was attended by 25 odd (operational) people from various humanitarian organisations (MSF, Red Cross, World Vision, ACAPS, CDAC …) with among them quite a few familiar faces. The aim of the workshop was quite ambitious and the question was not fully answered but it triggered some good discussion and useful connections were made. (BTW: What will happen to all the post-its? They never got discussed !?)
I managed to scribble down some remarks that stuck with me and these are dumped below. Its only a small, random subset of what was talked about but generally very similar in content to the Rescue Global workshop I wrote about in my last post.
I recently attended a workshop with Rescue Global (RG) and this blog post captures some of the discussion and points that are interesting and useful to digital humanitarians like myself. The better we understand how disaster response works (or doesn’t work) the better we can build our tools and get them used in anger.
Given my activity in the general Tech4Good space and autonomous systems I could not let Patrick’s announcement slide without doing a little post here to help spread the word.
One of the projects I have been involved with recently was a collaboration with the Agents, Interaction, and Complexity group at University of Southampton. The same group who we are also involved with in the Orchid project. This particular project was on Measuring and Predicting Departures from Routine in Human Mobility, building on the PhD work by James McInerney (now at Princeton) and his paper Breaking the Habit.
It is well known that humans generally follow very regular and predicable mobility patterns, both spatially and temporally. Lots of work has looked at exploiting and predicting those patterns but much less so on looking specifically at departures from those regular patterns. What can we learn from those departures from routine? How predictable are they?
Update: Unfortunately I purposely withdrew from the DL meetup after a very unprofessional experience with the co-organisers Persontyle. I Instead I joined forces with the London Machine Learning Meetup.
It has been almost half a year since I announced I would take over the London Big-O Algorithms meetup and bring it back to life. 5 Months later I am very happy to say all has gone extremely well, interest and attendance far exceeding my expectations. We have had a great set of meetups so far and all speaker slots are booked until June with talks from Google, The founder of ZeroMQ, Microsoft Bing, and many others. Really nice to see there is strong interest in good, solid, technical content.
However, enough about Big-O. This post is to announce a new meetup group that I have been convinced into setting up. The Deep Learning London meetup. The aim of this group is to bring together people interested in the family of machine learning methods that are concerned with learning distributed, hierarchical (“deep”) representations. Neural Networks being the most popular implementation. Its an area I have been looking at for a while and will be getting into quite deeply over the next couple of months (no pun intended). The format will be based around guest speakers sharing new research ideas and applications covering a wide range of fields from computer vision and natural language processing to autonomous systems and prognostics.
Note we are not assuming deep learning is the be-all end-all silver bullet of machine learning and welcome critical thoughts and benchmarks.
Sound interesting? Get in touch!