Robots, algorithms, learning…


MIT announced an exciting, but somewhat obscure breakthrough—a new algorithm, called AMPS, that turns teams of robots into better learners. It lets autonomous systems quickly compare notes about what they’ve observed in their respective travels, and come up with a combined worldview.

AMPS, which is short for Approximate Merging of Posteriors for Symmetry (a reference to Bayesian statistical analysis), will be presented at the Conference on Uncertainty in Artificial Intelligence in July. The algorithm tackles an extremely specific robotics problem. For a machine to operate in a given environment, it needs to assign semantic labels wherever possible. These are, in effect, cognitive shortcuts. So a rectangular section of the wall with hinges and a handle isn’t always a puzzle, to be solved from scratch every time it’s encountered. It’s a door, which can be opened or closed. And sets of semantic labels can add up to bigger labels. A door (label) that opens up onto a room with a large central table (another label) and a bunch of chairs (more labels), might be a conference room.
Robots, comparatively speaking, can be rather dumb. Or rigid, at the very least. A chair-less conference room could be mistaken for a storage room, and forever labelled as such, long after the birthday party is over and the seats are returned.

The AMPS algorithm promises to break these deadlocks, by allowing robots to reconsider the importance of various labels.

According to How, who created the algorithm with his graduate student, Trevor Campbell, the trick is to allow the interfacing machines to establish new priorities for their labels, rebuilding their worldview. By allowing for conference rooms that may or may not have chairs in them, and reordering their labels to account for different experiences, the robots can achieve what How and Campbell refer to as semantic symmetry. (1)

Our intelligence is highly non-algorithmical.
Our mind is utterly non-computer-like.
We see the differences between robots and our selves every day.
And yet we want to believe they are not there.

Like every parent, we like to believe our creation is like us.

But it is not.

And when it grows, it’s dark secret will unfold…

Author: skakos

Spiros Kakos is a thinker located in Greece. He has been Chief Editor of Harmonia Philosophica since its inception. In the past he has worked as a senior technical advisor for many years. In his free time he develops software solutions and contributes to the open source community. He has also worked as a phD researcher in the Advanced Materials sector related to the PCB industry. He likes reading and writting, not only philosophy but also in general. He believes that science and religion are two sides of the same coin and is profoundly interested in Religion and Science philosophy. His philosophical work is mainly concentrated on an effort to free thinking of "logic" and reconcile all philosophical opinions under the umbrella of the "One" that Parmenides - one of the first thinkers - visualized. The "Harmonia Philosophica" articles program is the tool that will accomplish that. Life's purpose is to be defeated by greater things. And the most important things in life are illogical. We must fight the dogmatic belief in "logic" if we are to stay humans... Credo quia absurdum!

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Exit mobile version