Recent strides in artificial intelligence from big name players such as Google, Facebook, and Baidu
, as well as increasingly successful heterogenous systems like IBM’s Watson have provoked fear and excitement
amongst the intelligentsia in equal measures. Public figures, such as Steven Hawking
, are concerned, and not surprisingly the popular press are excited to cover it. Recently, Elon Musk has become worried that AI might eventually spell doom for the human race
. He donated $10 million
to fund the Future of Life
organization whose stated goal is to ensure AI remains beneficial and does not threaten our wellbeing. An open letter
by this organization, titled “Research Priorities for Robust and Beneficial Artificial Intelligence,” was signed by hundreds of research leaders. Influential futurist, Ray Kurzweil, has popularized the idea of the technological singularity
where intelligent systems surpass human capabilities and leave us marginalized at best. Continue reading
I read with interest the recent paper out of Baidu about scaling up image recognition
. In it they talk about creating a supercomputer to carry out the learning phase of training a deep convolutional network. Training such things is terribly slow, with their typical example taking 212 hours on a single GPU machine because of the enormous number of weight computations that need to be evaluated and the slow stochastic gradient process over large training sets.
Baidu has built a dedicated machine with 36 servers connected by an InfiniBand switch, each server with four GPUs. In the paper they describe different ways of partitioning the problem to run on this machine. They end up being able to train the model using 32 GPUs in 8.6 hours. Continue reading
In recent years the concept of deep learning has been gaining widespread attention. The media frequently reports on talent acquisitions in this field, such as those by Google and Facebook, and startups which claim to employ deep learning are met with enthusiasm. Gratuitous comparisons with the human brain are frequent. But is this just a trendy buzz word? What exactly is deep learning and how is it relevant to developments in machine intelligence?
For many researchers, deep learning is simply a continuation of the multi-decade advancement in our ability to make use of large scale neural networks. Let’s first take a quick tour of the problems that neural networks and related technologies are trying to solve, and later we will examine the deep learning architectures in greater detail.
Machine learning generally breaks down into two application areas which are closely related: classification and regression. Continue reading
Recently NASA has been in the news with the successful launch and recovery of the Orion space craft
. This was a four hour two orbit test of the new capsule that is intended to support future manned missions beyond the Earth. In addition, there has been a huge growth of the space industry in the last decade including commercial ventures such as Space X
and Blue Origin
, as well as proposals to mine the asteroids
. There is always a tremendous interest in sending people to space, and in fact it seems to be an imperative for the human race to escape potential future disaster scenarios on the Earth by seeking solace among the stars. Continue reading
I am currently working on improving this blog and putting more projects and documentation on here that might be useful or interesting for people to see. I’ve spent a long time looking for a slightly better theme, but every time I find something I like, it ends up being the case that it won’t install properly or else it has issues on mobile, etc. Most frustrating. I’m trying to make the blog a bit easier to use from mobile devices.
I’m doing some simple exploration of image statistics on a large database of natural images. The first thing that I tried was computing the histogram of neighboring image pixel intensity differences. Here is the graph for that using a log y axis, for a few pixel separations.
It is clear that large differences occur much more rarely and that the most probable pixel to pixel spatial change in intensity is zero. However the tails are heavy, so it is nothing like a Gaussian distribution. The adjacent pixel intensity difference log probabilities were fairly well fitted by a function that goes like
, and the pixels further apart require a smaller exponent. Continue reading
Make magazine published an article about my relay calculating machine project. Click on the picture for a high-res version. You can watch a video on the project page here
I created a graphic design app for the iPad last year called Tree Crafter that lets you create tree inspired organic vector art and animations. It is fun to play with and quite relaxing. Also you can create great designs for web graphics or for merchandise with relative ease.
Recently I built a new web site for this app: http://treecrafter.com
If you have an iPad you should give it a go and let me know what you think. I am very keen to get it reviewed, so if you are an app reviewer, I can give you a promo code if you would like to write about it.
I received the good news that my Relay Calculating Engine
has been accepted for showing at the Maker Faire
in San Francisco in May. I’m looking forward to taking it down there and showing it to interested people.Make Magazine
also interviewed me about this project and plan to feature the work too. I’m excited to see what they write about it.
My main concern is to finish it and get it all working in time for May. This should not be a problem since I currently have the luxury to be able to work full time on the project and at present, I am about 90% complete.
I hope that you can come along and check it out. I will also be showing some of the other projects on which I have been working. I’ll also be attending the Seattle Mini Maker Faire, but not showing anything off there.
This is part 3 of my series of posts on the statistics of financial markets. Part 1 is here
In previous posts, I have found that working in log prices makes sense and that the double exponential distribution is a good fit to price change data. In this post, I will look at correlations over time in price changes.
Let’s ask a simple question: Does yesterday’s price change predict today’s price change? Continue reading