Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5

Computers evolve a new path toward human intelligence

#1
C C Offline
https://www.quantamagazine.org/computers...-20191106/

EXCERPT: . . . Kenneth Stanley is a pioneer in a field of artificial intelligence called neuroevolution, which co-opts the principles of biological evolution to design smarter algorithms. [...] One day Stanley spotted something resembling an alien face on the site [Picbreeder]and began evolving it, selecting a child and grandchild and so on. By chance, the round eyes moved lower and began to resemble the wheels of a car. Stanley went with it and evolved a spiffy-looking sports car. He kept thinking about the fact that if he had started trying to evolve a car from scratch, instead of from an alien, he might never have done it, and he wondered what that implied about attacking problems directly. “It had a huge impact on my whole life,” he said. He looked at other interesting images that had emerged on Picbreeder, traced their lineages, and realized that nearly all of them had evolved by way of something that looked completely different. “Once I saw the evidence for that, I was just blown away.”

Stanley’s realization led to what he calls the steppingstone principle — and, with it, a way of designing algorithms that more fully embraces the endlessly creative potential of biological evolution. Evolutionary algorithms have been around for a long time. Traditionally, they’ve been used to solve specific problems. In each generation, the solutions that perform best on some metric — the ability to control a two-legged robot, say — are selected and produce offspring. While these algorithms have seen some successes, they can be more computationally intensive than other approaches such as “deep learning,” which has exploded in popularity in recent years.

The steppingstone principle goes beyond traditional evolutionary approaches. Instead of optimizing for a specific goal, it embraces creative exploration of all possible solutions. By doing so, it has paid off with groundbreaking results. Earlier this year, one system based on the steppingstone principle mastered two video games that had stumped popular machine learning methods. And in a paper published last week in Nature, DeepMind — the artificial intelligence company that pioneered the use of deep learning for problems such as the game of Go — reported success in combining deep learning with the evolution of a diverse population of solutions.

The steppingstone’s potential can be seen by analogy with biological evolution. In nature, the tree of life has no overarching goal, and features used for one function might find themselves enlisted for something completely different. Feathers, for example, likely evolved for insulation and only later became handy for flight.

Biological evolution is also the only system to produce human intelligence, which is the ultimate dream of many AI researchers. Because of biology’s track record, Stanley and others have come to believe that if we want algorithms that can navigate the physical and social world as easily as we can — or better! — we need to imitate nature’s tactics. Instead of hard-coding the rules of reasoning, or having computers learn to score highly on specific performance metrics, they argue, we must let a population of solutions blossom. Make them prioritize novelty or interestingness instead of the ability to walk or talk. They may discover an indirect path, a set of steppingstones, and wind up walking and talking better than if they’d sought those skills directly. (MORE - details)
Reply


Possibly Related Threads…
Thread Author Replies Views Last Post
  Research Physicists finally find a problem only quantum computers can do C C 2 28 Mar 15, 2024 02:49 AM
Last Post: confused2
  Article A new approach to computation reimagines artificial intelligence C C 1 76 Apr 15, 2023 08:44 AM
Last Post: Kornee
  Another path to intelligence that's not AI C C 1 86 Aug 19, 2022 06:35 PM
Last Post: Magical Realist
  We're building computers wrong + Using AI to find anomalies hid in massive datasets C C 0 81 Mar 3, 2022 06:06 PM
Last Post: C C
  How exascale computers can verify the universe C C 3 141 Oct 19, 2021 12:13 PM
Last Post: Zinjanthropos
  New report assesses progress and risks of artificial intelligence C C 0 73 Sep 17, 2021 01:58 AM
Last Post: C C
  It's hard to give computers common sense Leigha 1 98 Aug 19, 2021 07:16 AM
Last Post: stryder
  Computer scientists discover new vulnerability affecting computers globally C C 0 172 May 2, 2021 09:42 PM
Last Post: C C
  The new oracles & gods: When people trust computers more than other humans C C 0 118 Apr 14, 2021 07:08 PM
Last Post: C C
  Why computers will never write good novels C C 3 170 Mar 31, 2021 04:35 PM
Last Post: Leigha



Users browsing this thread: 1 Guest(s)