Collaborative learning — for robots
Algorithm lets independent agents collectively produce a machine-learning model without aggregating data.
Algorithm lets independent agents collectively produce a machine-learning model without aggregating data.
Applications could include educational tools, systems to solve practical geometry or physics problems.
An algorithm that extends an artificial-intelligence technique to new tasks could aid in analysis of flight delays and social networks.
With a recently released programming framework, researchers show that a new machine-learning algorithm outperforms its predecessors.
Computer scientists and electrical engineers are devising algorithms that look for useful new patterns in data produced by medical sensors.
For database-driven applications, new software could reduce hardware requirements by 95 percent while actually improving performance.
A new approach to algorithmically distinguishing words with multiple possible meanings could help find useful data in electronic medical records.
A new system allows Excel users to create customized functions for their spreadsheets simply by offering a few examples of how data should be manipulated.
A new technique for finding relationships between variables in large datasets makes no prior assumptions about what those relationships might be.
New math will make it much easier to build machine-learning systems that tackle a wider range of problems.