deepstash
Beta
Computers Evolve a New Path Toward Human Intelligence | Quanta Magazine
Pros and Cons of Neuroevolution
- It requires a considerable amount of computation.
- Most people want to solve a particular problem. Neuroevolution might get you to a creative solution but could lead you astray before it puts you on the right path.
Pros
- Other AI, like reinforcement learning, can lead to short-terms gains, but will eventually get stuck in a rut. Random exploration in the steppingstone principle can beat the best algorithms.
- Open-ended exploration might lead to human-level intelligence via paths we would never have anticipated.
36 SAVES
This is a professional note extracted from an online article.
Read more efficiently
Save what inspires you
Remember anything
IDEA EXTRACTED FROM:
7
Key Ideas
Neuroevolution
Neuroevolution is a form of artificial intelligence. It is a meta-algorithm, an algorithm for designing algorithms. It adopts the principles of biological evolution in order to design smarter algorithms. Eventually, the algorithms get pretty good at their job.
Evolutionary algorithms
Traditionally, evolutionary algorithms are used to solve specific problems. For instance, the ability to control a two-legged robot. Solutions that perform the best on some metrics are selected to produce offspring.
In spite of successes, these algorithms are more computationally intensive than approaches such as "deep learning."
The steppingstone principle
It goes beyond traditional evolutionary approaches. It explains innovation. Instead of optimizing for a specific goal, it embraces the creative exploration of a diverse population of solutions.
The steppingstone’s potential can be seen by analogy with biological evolution: feathers likely evolved for insulation and only later became handy for flight.
Producing human intelligence
Biological evolution is the only system to produce human intelligence.
If we want algorithms that can navigate the physical and social world as we do, we need to imitate nature's tactics. Instead of hard-coding for specific metrics, we must let a population of solutions blossom that may discover an indirect path or a set of stepping stones to allow them to evolve better than if they'd received those skills directly.
Pursuing objectives can be problematic
Pursuing specific goals can be a hindrance to reaching those objectives.
Kenneth Stanley, a computer scientist, hoped to show that by following ideas in interesting directions, algorithms can produce a diversity of results and solve problems. Thus, ignoring an objective can get you to the solution faster than pursuing it. He showed this through an approach named novelty search.
Pros and Cons of Neuroevolution
- It requires a considerable amount of computation.
- Most people want to solve a particular problem. Neuroevolution might get you to a creative solution but could lead you astray before it puts you on the right path.
Pros
- Other AI, like reinforcement learning, can lead to short-terms gains, but will eventually get stuck in a rut. Random exploration in the steppingstone principle can beat the best algorithms.
- Open-ended exploration might lead to human-level intelligence via paths we would never have anticipated.
Main uses of evolutionary algorithms
- Maintaining a population of different solutions
- Optimizing a single solution.
SIMILAR ARTICLES & IDEAS:
4
Key Ideas
Safe To Forget
As machines become increasingly capable, along with computer memory, power and space being abundantly available, our brains are in a transition phase.
Earlier we had to remember a lot, do cal...
Information In Your Head
As technology advances and the internet gets dramatically more powerful, the need to retain information in our heads diminishes.
Google and other search engines which deploy AI, work as our 'memory partners' and provide us access to most of the human knowledge.
Peer-To-Peer Memory Networks
Our ancestors had a manual 'peer-to-peer' memory network to pass on knowledge to the future generations; it wasn't reliable but worked for a long time.
Now we believe AI is better and more objective to provide us with information, which might not be the case.
one more idea
1
Key Idea
Connectional intelligence
The ability to drive innovation and breakthrough results by tackling the power of relationships and networks.
It recognizes that leaps in creativity and progress cannot be achieve...
5
Key Ideas
TikTok
TikTok is reportedly 500 million users strong. It’s been a while since a new social app got big enough to make nonusers feel they’re missing out from an experience.
TikTok is an app for...
TikTok "tools"
- Filters as on Snapchat.
- The ability to search for sounds to score your video.
- It provides extensive reasons and prompts.
- Hashtags play a large role as a functional organizing principle.
- It nudges you and makes it easy to come up with material to post.
- Users are encouraged to engage with other users in two ways: Through "response" videos and through "duets" where a user replicates a video and add themselves alongside.
Fundamentally different
TikTok has stepped over the point between the familiar self-directed feed and experience based on algorithmic observation and inference. When you open the app, you don't see a feed of your friends, but a page called "For You" - It's an algorithmic feed based on videos you've interacted with or just watched.
It's not full of people you know or things you've explicitly told it you want to see. It is constantly learning from you and builds up a model of what you tend to watch. In short, it is like an Instagram centered entirely around its "Explore" tab.
2 more ideas