So, day one of the ReWork Deep Learning Summit Boston 2015 is over. A lot of interesting talks and demonstrations all round. All talks were recorded so I will update this post as they become available with the links to wherever the recordings are posted – I know I’ll be rewatching them.
Following a brief introduction the day kicked off with a presentation from Christian Szegedy of Google looking at the deep learning they had set up to analyse YouTube videos. They’d taken the traditional networks used in Google and made them smaller, discovering that an architecture with several layers of small networks was more computationally efficient that larger ones, with a 5 level (inception-5) most efficient. Several papers were referenced, which I’ll need to look up later, but the results looked interesting.
While on my flight to Boston for ReWorkDL I watched Ex Machina the “must see” latest AI film. I’d been warned that it wasn’t very good by my husband (who’d just flown home the day before!) but I thought that since he’d already seen it, I’d better take the chance to watch it since it’s unlikely to be something we’d watch together in the future. If you haven’t seen it, then please be aware that this post does contain spoilers so read on with caution. Continue reading Ex Machina – film review
At the end of my last post, we had a completed y-axis and had also built the main frame of the printer, this post looks at building the x-axis assembly, covering issues 16 to 19 of 3D Create and Print by Eaglemoss Technology. If you’ve skipped a part of this series you can start from the beginning, including details of the Vector 3 printer I’m building on my 3D printer page.
While this is mainly an exact copy of the steps that we undertook for the y-axis, we are working directly on the mainframe, which presents its own challenges. There are a few tips I suggest to make life a little easier for yourself, especially if you’ve been saving parts or have received several issues in the same drop.
If you’ve been following this blog you’ll know that I’ve started a new role that requires me to build a deep learning system and I’ve been catching up on the 10+ years of research since I completed my PhD. With a background in computing and mathematics I jumped straight in to what I thought would be skimming through the literature. I soon realised that it would be better all round to jump back to first principles rather than be constrained with the methods I had learned over a decade ago.
So, I found a lot of universities who had put their machine learning courses online and have decided to work through what’s out there as if I was an undergraduate and then use my experience to build on top of that. I don’t want to miss an advantage because I wasn’t aware of it.
I’ve never thought of myself as a gender activist, and I think this is partly because I’ve never felt treated poorly – I’ve had equality throughout my life and have never felt the pull to be an activist, and as the years go by I am aware of how much privilege this background has afforded me, something that has made me start supporting those who were not as fortunate. This evening I watched a conversation unfold on twitter that annoyed me, so I’m going to put aside the tech and maths for a moment and look at what the problem is and what it isn’t.
Dr Sue Black had been giving a talk at an event in London about her TechMums program, which aims to teach women how to code to better understand technology, not necessarily to get jobs as programmers. This is a fantastic initiative and one of many that opens up understanding to people who may otherwise be ignorant on a subject that they may never have covered at school. I’ll come on to why this is important later. However, the inflammatory tweet was:
I’m four weeks in to my new role and one of the threads of work I have is looking into machine learning and how this has advanced since my own thesis. The current approach to machine intelligence is via learning networks where the data is abstracted: rather than recognising specifics about the problem, the algorithm learns the common elements of the problem and solution to match an input to the expected output, without needing an exact match. Our brains are very good at this: from a very early age we can recognise familiar faces from unfamiliar ones and quickly this progresses to identification in bad light, different angles, when the face is obscured. Getting machines to do the same has been notoriously difficult. Continue reading Machine intelligence – training and plasticity
So, in my last post we completed the Y-axis motor assembly and tested it. Issues 11-15 of the 3D Create and Print magazine will see us add the cover and bracket for the y-axis and start on the printer plates and feet. If you’ve skipped a part of this series you can start from the beginning, including details of the Vector 3 printer I’m building on my 3D printer page.
Y-axis cover: This is a fairly simple 3-bolt step. The only real gotchas here are to ensure that the cover is on the correct way round (so the slot in the cover is closest to the motor) and that the wires from the limit switch are not caught in any of the other parts and thread out through the slot. Yes there are only meant to be three bolts at this stage 🙂 This is also one of the first bad designs I’ve noticed – the y-axis could benefit from an extra clip to secure the limit switch wires because, now they are hidden, they could easily be too close the the motor belt and get worn down. Should the printer stop working, this will be one of the the first things I check.
If you’ve been watching anything on Channel 4 recently you’ll have seen a trailer for PersonaSynthetics – advertising the latest home must-have gadget. The ad itself is slightly creepy, despite the smiling family images, and the website supports this sterile AI view to an extent that some people have expressed concern over a genuine product being available. It’s a fantastic ad campaign for their new series Humans, which in itself looks like it’d be worth a watch (there’s a nice trailer on the website), but it has raised again the issues around artificial intelligence, and how far should it go.
This is of particular interest to me as I am starting a new project in machine learning and, while my work isn’t going to lead to a home based automaton, there are some interesting questions to be considered in this area to ensure that we don’t end up making ourselves obsolete as a species. Continue reading Artificial Intelligence
I’ve had a few discussions recently as to why I’m building a 3D printer using one of these collect the parts magazine rather than either a) buying one outright or b) getting a “proper” build-it-yourself kit from an online store. Now seems like a reasonable time to address the reasons behind this.
If you’ve been following my 3D printing posts you’ll know I’ve subscribed to Eaglemoss’ 3D Create and Print magazine and am gradually building my own printer. With the weekly cost of the magazine this will eventually cost me £650 and I won’t have a complete printer until the middle of next year. While this is cheaper than buying one outright now, with the speed of change and improvement it’s likely that the printer will be out of date, and this is not the only argument:
Following from building the Y-axis assembly of my 3D printer, this post covers the fitting of the motor and the circuit boards to test, using the pieces in issues 7 to 10 of the 3D Create and Print magazine. It’s a good job that, even though this is a “weekly” magazine, the issues arrive in sets of four as otherwise I imagine it could be very frustrating waiting, not able to add to the printer, until issue 10.
I don’t actually see why this stage was any different to the earlier steps – if the pieces had been delivered in a different order then there would have been no need to wait until the 10th issue before starting. I can only assume that someone may have been tempted to power it all up before it was ready, which is why the motor itself is the last piece from this stage to arrive. Continue reading 3D Printer Part 3: Y-axis motor and testing