Distributed Coordination and Network Structure: Experimental Results from Simulation

AAAI Conferences

Coordination is an important phenomena occurring in a wide variety of social and technical systems. We use simulation to examine the ways in which one important system property, the interaction network, effects overall levels of coordination. In particular, we survey the performance of six different learning algorithms, including reasonable strategies and no regret strategies on networks generated by six different algorithms. Our results suggest that no-regret mechanisms not only perform better but also come closer to replicating human behavior in the network coordination task.


Deep learning: What's changed?

#artificialintelligence

Deep learning made the headlines when the UK's AlphaGo team beat Lee Sedol, holder of 18 international titles, in the Go board game. Go is more complex than other games, such as Chess, where machines have previously crushed famous players. The number of potential moves explodes exponentially so it wasn't possible for computers to use the same techniques used in Chess. In learning Go, the computer would have to create millions of games, competing against itself and discovering new strategies that humans may never have considered. Deep learning itself isn't that new, and researchers have been working on algorithms for many years, refining the approach and developing new algorithms.


Deep learning: what's changed?

#artificialintelligence

Deep learning made the headlines when the UK's AlphaGo team beat Lee Sedol, holder of 18 international titles, in the Go board game. The number of potential moves explodes exponentially so it wasn't possible for computers to use the same techniques used in Chess. In learning Go, the computer would have to create millions of games, competing against itself and discovering new strategies that humans may never have considered. Deep learning itself isn't that new, and researchers have been working on algorithms for many years, refining the approach and developing new algorithms. What has stimulated it recently is the convergence of massively parallel processing, huge data sets and superior performance against traditional machine learning algorithms.


Deep Learning Tutorials -- DeepLearning 0.1 documentation

#artificialintelligence

Deep Learning is a new area of Machine Learning research, which has been introduced with the objective of moving Machine Learning closer to one of its original goals: Artificial Intelligence. See these course notes for a brief introduction to Machine Learning for AI and an introduction to Deep Learning algorithms. Deep Learning is about learning multiple levels of representation and abstraction that help to make sense of data such as images, sound, and text. The tutorials presented here will introduce you to some of the most important deep learning algorithms and will also show you how to run them using Theano. Theano is a python library that makes writing deep learning models easy, and gives the option of training them on a GPU.


How Machine Learning Algorithms Help Businesses Target Their Ads

#artificialintelligence

It happens all the time. One minute, you're Googling, "what is a differential?" The next minute, you're looking at toasters on Amazon or exercise equipment on eBay, and all you see everywhere are pictures of axle girdles and Trac-Lot rebuild kits. If the internet is going to flood your senses with ads anyway, they might as well be ads for things you're interested in. But how do they do it?