21–30 of 40 posts
Some interesting ideas sadly blocked behind a pay-wall journal, all for the purpose of boosting a researcher's prestige because they now hold a "Nature" publication. Thankfully, this article is easily accessible via Sci-Hub. http://www.nature.com.sci-hub.cc/nature/journal/vaop/ncurren...
Here's an official, publicly accessible, link to the article: http://rdcu.be/kXhV
One of the examples given is a block puzzle (reorder 8 pieces in a 3x3 grid back into order) Has this been a problem for AI and CNN's?
The progress in the article is getting a learning system to do so, eventually leading us to handle unsolved problems.
Could it learn to use addresses that perform more interesting functions than f(x)=x?
One of the examples given is a block puzzle (reorder 8 pieces in a 3x3 grid back into order) Has this been a problem for AI and CNN's?
That problem was solved by a non learning AI system decades ago. Current theorem provers (a related field of AI) solve problems like this in fractions of a second. The progress in the article is getting a learning system to do so, eventually leading us to handle unsolved problems.
What kinds of other unsolved problems are out there? I'm always looking for something interesting.
Neural networks are great at pattern recognition. Things like LSTMs allow pattern recognition through time, so they can develop "memories". This is useful in things like understanding text (the meaning of one word often depends on the previous few words).
But how can a neural network know "facts"?
Humans have things like books, or the ability to ask others for things they don't know. How would we build something analogous to that for neural network-powered "AIs"?
There's been a strand of research mostly coming out of Jason Weston's Memory Networks research[1]. This extends on that by using a new form of memory, and shows how it can perform at some pretty difficult tasks. These included graph tasks like London underground traversal.
One good quote showing how well it works:
In this case, the best LSTM network we found in an extensive hyper-parameter search failed to complete the first level of its training curriculum of even the easiest task (traversal), reaching an average of only 37% accuracy after almost two million training examples; DNCs reached an average of 98.8% accuracy on the final lesson of the same curriculum after around one million training examples.
Earlier quoted context omitted.
That problem was solved by a non learning AI system decades ago. Current theorem provers (a related field of AI) solve problems like this in fractions of a second. The progress in the article is getting a learning system to do so, eventually leading us to handle unsolved problems.
Interesting. I have an AI agent that can solve these types of problems. What kinds of other unsolved problems are out there? I'm always looking for something interesting.
One of the examples given is a block puzzle (reorder 8 pieces in a 3x3 grid back into order) Has this been a problem for AI and CNN's?
That problem was solved by a non learning AI system decades ago. Current theorem provers (a related field of AI) solve problems like this in fractions of a second. The progress in the article is getting a learning system to do so, eventually leading us to handle unsolved problems.
i.e, in the blog post it discusses using the network to find the shortest path between two stations, would the steps to do that look like this?
1. Train the NN how to navigate any network, presenting the graph data each time you ask the NN a problem 2. take the trained NN and feed it the London Underground, then ask it to tell you how to get there?
This is probably the most important research direction in modern neural network research. Neural networks are great at pattern recognition. Things like LSTMs allow pattern recognition through time, so they can develop "memories". This is useful in things like understanding text (the meaning of one word often depends on the previous few words). But how can a neural network know "facts"? Humans have things like books,…