Jeff – OverCloud

Hyperdimensional Active Perception

A new approach to integrating sensory input and responsive action– an intriguing paper: “Learning Sensorimotor Control with Neuromorphic Sensors: Toward Hyperdimensional Active Perception” by Anton Mitrokhin and Peter Sutor (abstract link)

Cogitai’s learning agent lives in the cloud, but it’s not called Skynet.

Cogitai has announced a Reinforcement Learning SaaS system called Continua. It has the potential to bring AlphaGo-like continual learning agents from the lab into the mainstream.

Boldness Reified

In case you missed this epic solo, Alex Honnold has free soloed another difficult, bold route, this time at Fair Head, Northern Ireland:
The Complete Scream, rated E8 6b (5.12+ R/X)

MOTHER OF ALL EPIC SOLO UPDATES:
Honnold Completes First Solo of El Cap
Free Solo

I swear I will never whine on lead again.

Victor Korchnoi: Uncompromising chess fighter

Today the chess world mourns the passing of Victor Korchnoi, a prolific and tremendous chess fighter.

Despite his skill and uncompromising approach to chess, he did not succeed in his ultimate quest to become World Champion– indeed, he is regarded as being the strongest grandmaster never to have become a World Champion (although Paul Keres and David Bronstein may have a claim to that as well).

One of my all-time favorite chess books is Korchnoi’s Chess is My Life.

Salute, Victor!

Continual Learning AI startup Cogitai teams up with Sony

Cogitai, Inc. is dedicated to building artificial intelligences (AIs) that learn continually from interactive experience with the real world.

Sony joins forces with Cogitai

A complete discussion of continual learning can be found in Mark Ring’s dissertation, Continual Learning in Reinforcement Environments.

I guess it is time to sign up for a machine learning course. This one by Littman (Cogitai) Isbell (Cogitai) and Kolhe looks good.

See: Cogitai

UPDATE (6/6/2016):

In case Cogitai and other AI agent builders are becoming _too_ successful, the human race are investigating the possibility of an AI agent “kill switch”.

Interestingly, while the Conclusion states:

… We have shown that some algorithms like Q-learning are
already safely interruptible, and some others like Sarsa are
not, off-the-shelf, but can easily be modified to have this
property. We have also shown that even an ideal agents
that tends to the optimal behaviour in any (deterministic)
computable environment can be made safely interruptible.

However, we may not be safe from Skynet Apocalypse, as the Conclusion also suggests:

… However, it is unclear if all algorithms can be easily made
safely interruptible …

Dean Potter

There is a different way to live, and you shouldn’t feel that you’re forced to do anything but what your one life should be. And the one life should be following your passion and doing that unique thing that only you are perfect for.

Celebrating the life of Dean Potter