My Halloween lecture has been uploaded to youtube. The basic outline is:
* what is intelligence?
* Solomonoff induction
* Hutter’s AIXI
* Monte Carlo AIXI (here’s the missing video of it playing pac-man)
* universal intelligence measure
* what neuroscience can teach us about AGI design
* early 2020’s: the Halloween scenario
You can get the slides here. I [...]
Model-free reinforcement learning (RL) algorithms are computationally cheap as each state-action pair keeps a cached estimate of its value that can easily be looked up in order to make a decision. Their weakness is that they are not easy to update when the agent’s goals, or the state of the world, changes in some [...]
Imagine the world: all the countries, all the towns, all the cities, all the mega cities, and all the 6 billion people living in them. Think about all the places you’ve been too, and all the places you haven’t been to, and just try to get a sense of the vastness of this for a [...]
If Roadrunner is a bit beyond your budget, simulating neural networks with GPUs might be an option:
The next generation of Nvidia GPUs will support enhancements such as double precision floating point in order to make them more suitable for general purpose highly parallel computation. There will also be cards with no graphics interface [...]
I just saw another neuroscience paper on neural correlates of consciousness. When I first heard about this idea in a lecture series given by Christof Koch, I thought it was a good idea. I now suspect, however, that this line of research is going to produce very little. What it will probably [...]