Profile cover photo
Profile photo
Philip Thrift
The cosmos is made of code.
The cosmos is made of code.
About
Philip's posts

Post has attachment

Post has shared content
Playing with the new Google Vision API: bit.ly/21ByQ1p - and it's pretty darn impressive! Fed it a bunch of random food shots, and the results are... really good.
Photo

Post has shared content

Post has shared content
Learn about Category Theory from a master, French mathematician Pierre Schapira, writing for the new Inference magazine: "Here I will consider uniqueness, or, rather, the concept of identity, and how it functions. I will therefore address the status of equality in mathematics and its variants, namely isomorphism, equivalence, and so on. This issue has until recently been totally ignored, but is of such importance that it may potentially lead us to question set theory itself." Fun and illuminating piece. The French version is available as well:

http://inference-review.com/article/categories-de-zero-a-linfini

Post has shared content

Post has attachment

Post has attachment

Post has attachment
ref:
Using Stories to Teach Human Values to Artificial Agents
<www.cc.gatech.edu/~riedl/pubs/aaai-ethics16.pdf>

Post has shared content
Interview with Leslie Valiant, a computer scientist attempting to formalize a fundamental equivalence between the capabilities of brains and computers. "Learning is a very reproducible phenomenon -- like an apple falling to the ground. Every day, children all around the world learn thousands of new words. It's a large-scale phenomenon for which there has to be some quantitative explanation. So I thought that learning should have some sort of theory. Since statistical inference already existed, my next question was: Why was statistics not enough to explain artificial intelligence? That was the start: Learning must be something statistical, but it's also something computational. I needed some theory which combined both computation and statistics to explain what the phenomenon was."

"All the knowledge an individual has must have been acquired either through learning or through the evolutionary process. And if this is so, then individual learning and evolutionary processes should have a unified theory to explain them."

Post has shared content
Huge news from our colleagues at DeepMind. Go was long considered a key problem for AI, because it's a game for which the 'try all combinations and see which does best' is simply not possible, and human Go players rely heavily on abstract pattern recognition to guide their decisions. This is further evidence that human-level pattern recognition is no longer a 'science' problem per-se (but still a mighty engineering problem). It's time for us to focus more on exploring higher levels of cognition.
Wait while more posts are being loaded