News for hackers. Stuff that matters.
Re:Machine learning is fundamentally conservative by kitsuac on Saturday January 04, 2020 @03:17AM (#21953643)
Without AGI there are still cases when the lower probability prediction will be better, and will lead to escaping a local minima. I'd argue that the potential benefits of calibrating that axis dynamically exist with or without AGI.
Re:Machine learning is fundamentally conservative by ben_w on Saturday January 04, 2020 @03:58AM (#21953791)
Are you describing the explore/exploit tradeoff or simulated annealing in this case?