The project

It is widely believed that "A computer produces nothing more than you put into it." The goal of the project is to prove that this belief is fundamentally wrong.

Who is ?

is still a one-person project, but it is the intention to share the effort as well as the fruits as widely as possible. Read on…

What's in a name?

The name is an acronym of four words that summarize the core principles that the project is based on: Learning Expectations Incrementally and Autonomously.

There are a lot of ways to approach A.I. To name a few: Neural Networks, Inductive Logic Programming, Evolutionary Programming, and Computer Vision. The approach of the project is Machine Learning. The main feature of learning is that a learner accumulates knowledge about its environment. This is the first way to prove the statement in the first paragraph on this page wrong. You don't put stuff into a learning system, on the contrary: a learning system gets knowledge out of its environment.
This keyword is meant to contrast with predictions. Predictions are black-and-white, they are also most of the time wrong. Expectations are more useful than predictions. You can bet on them, literally! This could turn out very helpful if we view learning as a betting game between a learning system and its environment.
Rather than studying for a case up front, thus keeping the learning phase and the evaluation phase separate, the project is designed around the principle: learn as you go along. Each fragment of interaction can lead to a change in behavior, and the system becomes more sophisticated in its responses in by successive increments.
This is the new element that this project introduces to machine learning: rather than a learning system that can learn a task, we strive for a learning system that is curious about its environment. An autonomous learning system may be constrained by internal limitations, but it is not depen­dent on its environment for teaching it. The environment does not supply losses or gains. This introduces a surprise factor that also aids in dis­proving the statement above.

Of course the autonomy principle implies that we have to study interactive systems. Curiosity implies actions and expectations imply responses, so let us create an A.I. that interacts…

"Thing" is an early example of interactive behavior out of a box

Visit the project page on GitHub for project details.