I’ve been putting together a page that collates the work I’ve done on 3DRC, including some more recent analysis. It’s a work-in-progress and might remain so perennially, but I’ve made it available here anyway 🙂 It includes some more videos … Continue reading →

A short proposal I made as part of a research fellowship application to an institute in Japan in Summer 2020. Modern agriculture is dominated by industrial farming methods that are heavily and increasingly reliant on robotic automation. These methods destroy … Continue reading →

Yes, the Royal Institution podcast recently published the audio recording of the discussion we had last year in London about the future of Artificial, perhaps General, Intelligence: https://soundcloud.com/royal-institution/a-generalist-ai-ri-science-podcast-45

It’s not so hard, though the gscript has to be published as a web app. Write the doGet function to retrieve the URL of the file in Drive, then return a small script that redirects to the URL using HtmlService. … Continue reading →

It’s amazing! I was invited to be part of a panel discussion on Artificial General Intelligence which took place yesterday. Quite a thrilling experience to be in the Royal Institution, talking about a subject I love, with extremely cool people: Wendy … Continue reading →

I wrote an article recently that commented on research by Nasr et al (link) that showed a machine learning engine discovering a sense of number: AI develops human-like number sense – taking us a step closer to building machines with … Continue reading →

Yes! It’s called Stoke-on-Tech and has a monthly-ish meeting at the wonderful Mitchell Arts Centre with free pizza, free beer, and most excitingly, free talks from inspiring speakers (although they did also suffer me doing one last week!). It’s worth … Continue reading →

Rather than just certain industries, let’s imagine that every job could, instead of by a human, be performed perfectly well by a machine. Everything that humanity currently produces is still produced, except that people stand at the sidelines and observe … Continue reading →

The second paper published at ALIFE 2018 was a continuation of my work with Jared Moore on Lexicase Selection. This poster presentation discussed the reasons why Lexicase performs well in our evolutionary robotics task.

I just returned from ALIFE 2018 where I presented a paper that describes using noise in the genotype-to-phenotype translation of evolved neural networks, when applied to robot control. I called this technique Stochastic Ontogenesis.