Podcast: Play in new window | Download (Duration: 5:34 — 3.5MB) | Embed
Bit seat drivers Deep learning algorithms, and neural networks in general, require much more training than humans do. They are unable to generalize well enough to handle situations not covered in the training data, and can be thrown off by things that a human wouldn’t even notice. Today we look at these challenges by examining …
Podcast: Play in new window | Download (Duration: 3:50 — 2.5MB) | Embed
do we need something else, or just more? Though deep learning has had some promising results, there are still some things that it simply doesn’t do well at. There are other algorithms that do as well or better at certain tasks. On the other hand, we’ve only been able to implement comparatively small neural networks. …
We’re in space, for reasons which are not explained. I’m the engineer, and it’s mostly about programming. There is a problem, and I need to make the AI software creatures solve it for us. It was a dream, and short on details.
I did a test where I had the code create a figure that was 36 safe random numbers long. A “safe random” number is a random number in a range equal to the lowest port number, and the memory array’s length. Port numbers are negative. 36 numbers is a max of 12 commands, unless the …
Podcast: Play in new window | Download (Duration: 6:42 — 4.0MB) | Embed
Use of graphics cards for neural networks Your graphics card holds a GPU—graphics processing unit. Unlike your CPU, which does one operation at a time, the GPU does many simple operations on many numbers at once. This allows your computer to run your favorite game, and it can be used to run artificial neural networks, …
Podcast: Play in new window | Download (Duration: 6:14 — 3.9MB) | Embed
Diving into deep learning Neural networks have had their ups and downs. However, in the last decade or so, they’ve really taken off. There were a couple of breakthroughs that made all the difference. Today we look at one of them, called “Deep Learning.” Here’s a 4-post long blog series on deep learning concepts and …
Podcast: Play in new window | Download (Duration: 4:46 — 3.0MB) | Embed
Evolving neural networks with polyworld Figuring out exactly what structure of a neural network could capture intelligence is a complicated problem. Why not let evolution do it for you? Today we look at Polyworld, where they did and are continuing to do that very experiment. Here’s a talk on polyworld and some of their results. …
Podcast: Play in new window | Download (Duration: 5:13 — 3.0MB) | Embed
Unsupervised learning When you are teaching an AI to solve a problem or do some task, you usually have to provide the right answer. However, sometimes, the AI can learn by itself, without being told what the right answer is.
Podcast: Play in new window | Download (Duration: 4:49 — 3.0MB) | Embed
Better and better Computers are being used to design computers. The better our computers and their tools get, the better computers and tools they can produce. But it wasn’t always an easy path. Today we look at the VAX9000. It used a system called “SID” to generate part of its design. SID was an expert …
Podcast: Play in new window | Download (Duration: 4:42 — 2.8MB) | Embed
An experiment in fuzzy logic Computers use Boolean logic. Everything is true false, yes no, zero and one. There are plenty of situations when a simple yes or no won’t cover it. To get a computer to handle those situations, one can use fuzzy logic. Today, we have an informal experiment that shows why fuzzy …