Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > comp.programming > #8690 > unrolled thread
| Started by | Sky89 <Sky89@sky68.com> |
|---|---|
| First post | 2018-04-21 23:54 -0400 |
| Last post | 2018-04-21 23:54 -0400 |
| Articles | 1 — 1 participant |
Back to article view | Back to comp.programming
About Deepmind's PathNet.. Sky89 <Sky89@sky68.com> - 2018-04-21 23:54 -0400
| From | Sky89 <Sky89@sky68.com> |
|---|---|
| Date | 2018-04-21 23:54 -0400 |
| Subject | About Deepmind's PathNet.. |
| Message-ID | <pbgivf$nhs$7@dont-email.me> |
Hello.... About Deepmind's PathNet.. I have read more about Deepmind's PathNet, and i have noticed that we are going from ‘narrow artificial intelligence’ to successfully addressing the three requirements of an artificial general intelligence like: positively transfer trained knowledge in supervised learning classification tasks and reinforcement learning tasks, read the following to notice it: Artificial intelligence up to now, including DeepMind’s AlphaGo, have been limited to perform well only for a specific task - hence the term ‘narrow artificial intelligence.’ But researchers are beginning to embrace the arrival of artificial general intelligence, an AI that can perform any task that a human can. In their recent paper, Google DeepMind proposes a method into training AGI by using genetic algorithm. So how well does PathNet perform in action? DeepMind’s experiments show that PathNet is faster than fine-tuning, and does positively transfer trained knowledge in supervised learning classification tasks and reinforcement learning tasks - successfully addressing the three requirements of an AGI. Read more here: http://www.deepbio.co.kr/2017/03/20/Weekly-paper-DeepMinds-PathNet.html Thank you, Amine Moulay Ramdane.
Back to top | Article view | comp.programming
csiph-web