Unsupervised Predictive Memory in a Goal-Directed Agent · HackerPapers discussions

Unsupervised Predictive Memory in a Goal-Directed Agent — mentioned by goolulusaurs

Sun, 03 Jun 2018 06:01:57 GMT

The Neural Turing Machine has been expanded upon considerably since that paper, and inspired a number of other memory augmented neural network architectures, including: https://www.gwern.net/docs/rl/2016-graves.pdf , https://arxiv.org/abs/1605.06065 and https://arxiv.org/abs/1803.10760 . If you don't want to read a bunch of papers this video also has a good discussion of that last paper, describing how a memory system based on the NTM has been applied to reinforcement learning to achieve very impressive results that seem to me to be a very significant step towards human-like general purpose…

Paper and discussion history. A mention is not an endorsement.

Unsupervised Predictive Memory in a Goal-Directed Agent — mentioned by nopinsight

Wed, 30 May 2018 05:50:11 GMT

The brain most likely has much more than a petaflop of computing power and it takes at least a decade to train a human brain to achieve the grandmaster level on an advanced board game. In addition, as the other comment says, they learn from hundreds or thousands of years of knowledge that other humans have accumulated and still lose to AlphaZero with mere hours of training. Current AIs have limitations but, at the tasks they are suited for, they can equal or exceed humans with years of experience. Computing power is not the key limit since it will be made cheaper over time. More importantly…

Paper and discussion history. A mention is not an endorsement.

Unsupervised Predictive Memory in a Goal-Directed Agent — HN submission

Tue, 29 May 2018 08:47:16 GMT

Unsupervised Predictive Memory in a Goal-Directed Agent

63 points; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Unsupervised Predictive Memory in a Goal-Directed Agent — mentioned by goolulusaurs

Wed, 18 Apr 2018 10:30:06 GMT

I'm also curious what your thoughts are on this paper: https://arxiv.org/abs/1803.10760 As a hobbyist/independent researcher I think it's really interesting to compare the two in terms of the way you model the environment and the parallels with neuroscience. It seems like their use of a DNC could address some of the points you mention about the limited historical capacity of LSTMs and catastrophic forgetting. I was very glad when I saw on github where you said the whole system could be trained in a reasonably short amount of time, because it makes it so much more feasible to try out and…

Paper and discussion history. A mention is not an endorsement.