Skip to main content

Machine learning needs stimulus for making solutions.

 

 Machine learning needs stimulus for making solutions. 




"A barren plateau is a trainability problem that occurs in machine learning optimization algorithms when the problem-solving space turns flat as the algorithm is run. Researchers at Los Alamos National Laboratory have developed theorems to prove that any given algorithm will avoid a barren plateau as it scales up to run on a quantum computer." (https://www.lanl.gov/discover/news-release-archive/2021/March/0319-barren-plateaus.php)

Have you heard of a "barren plateaus" problem? The name of that problem is coming from the J.R.R Tolkien book. Wherein the fictive Middle land is the very dry and hot place. The image, above this text, introduces the "barren plateaus" problem very well. 

In the next example, the food and water are the information. If a creature lives in the "fresh plateaus" it can take nutrients from nature. There is a bigger chance to make mistakes. But the nutrient is versatile and finding and testing new things makes the creature in the work. When a creature searches for things from nature there are many possibilities to test which type of vegetables or other nutrient sources the creature uses. Of course, that thing requires sometimes rise to the mountains. 

In that image, the problem is the mountain. The thing is that if the creature lives on the landscape at the higher image. That creature has stimulus. The green landscape offers motivation and the grass is the food and the creature wants to go to the mountain. The grass and water are everywhere and the creature has the motivation to rise to the mountain. And that could be willing to see the farter places. Or maybe the creature wants to get fresh air. 

The lower image introduces the situation. Where the creature lives in the "barren plateau". The water and food are in a pocket or bag and of course, the creature never makes mistakes if that creature wants to get a certain sandwich. The creature knows which pocket that creature can get sausage sandwich and where is the drinking bottle. But sooner or later, the nutrient would turn unilateral. In barren plateaus problem, the creature will get pre-made food. 

So if we are transferring that model to the information technology the creature will get pre-made solutions that fit in certain situations. And that makes this kind of model very limited. The situation is like that creature lives in the desert or "barren plateaus". The supporter brings water and sandwich to a certain point at a certain time. The food is guaranteed but it's always the same. 

And what the creature gets depends on the supporter. If the supporter wants to give the sausage sandwich that is the food. If someday the supporter wants to give the cheese sandwich that creature will get a cheese sandwich. 

When everything is pre-made the creature doesn't want to try itself to find food. There is difficult to make mistakes if some other person makes the food. The same way is in data science. If all problems are pre-solved that thing means that it's very hard to make wrong solutions. 

The term "flatten landscape" means that when the creature is living in "barren plateaus" the limited information sources makes the problems look harder to solve. Because the creature always is at a certain point where the supporter will bring a sandwich and water the creature is not even trying to climb mountains or solve the problem. 


"A barren plateau is a trainability problem that occurs in machine learning optimization algorithms when the problem-solving space turns flat as the algorithm is running".

"In that situation, the algorithm can’t find the downward slope in what appears to be a featureless landscape and there’s no clear path to the energy minimum. Lacking landscape features, machine learning can’t train itself to find the solution". (LosAlamos National laboratories, Solving ‘barren plateaus’ is the key to quantum machine learning)


https://www.lanl.gov/discover/news-release-archive/2021/March/0319-barren-plateaus.php


Image:https://www.lanl.gov/discover/news-release-archive/2021/March/0319-barren-plateaus.php


https://interestandinnovation.blogspot.com/


Comments

Popular posts from this blog

Use virtual "perpetual motion machines" and seawater as energy sources.

   Use virtual "perpetual motion machines"  and seawater as energy sources.  The Archimedean screw can offer almost endless energy sources.  "Robert Fludd's 1618 "water screw" perpetual motion machine from a 1660 wood engraving. It is widely credited as the first attempt to describe such a device." (Wikipedia/Perpetual motion) The term "virtual perpetual motion machine" means a machine. That pulls water to the upper tank using a capillary tube. Then that water will fall through the generator or turbine wheel. The machine uses differences in pressure levels. But it looks like a "perpetual motion machine", that is impossible because of laws of thermodynamics.  The machine uses differences in pressure levels. But it looks like a " real perpetual motion machine", which is impossible because of the laws of thermodynamics.  The real perpetual motion machines don't use outside energy. And that's why they are not possible.

Metamaterials can change their properties in an electric- or electro-optical field.

"Researchers have created a novel metamaterial that can dynamically tune its shape and properties in real-time, offering unprecedented adaptability for applications in robotics and smart materials. This development bridges the gap between current materials and the adaptability seen in nature, paving the way for the future of adaptive technologies. Credit: UNIST" (ScitechDaily, Metamaterial Magic: Scientists Develop New Material That Can Dynamically Tune Its Shape and Mechanical Properties in Real-Time) Metamaterials can change their properties in an electric- or electro-optical field.  An electro-optical activator can also be an IR state, which means. The metamorphosis in the material can thermally activate.  AI is the ultimate tool for metamaterial research. Metamaterials are nanotechnical- or quantum technical tools that can change their properties, like reflection or state from solid to liquid when the electric or optical effect hits that material. The metamaterial can cru

There might be an answer to why there is a gravitational hole in Earth's gravitational field.

The gravitational field at the point of the Indian Ocean is weaker than in other places on Earth. The existence of that gravitational hole is proved. But the reason why that gravitational hole is formed is unknown. The reason why the gravitational field on the Indian Ocean is weaker might be a simple thing.  There is a possible lighter rock in the mantle, or there is less material at that point. In some wildest theories, there are bubbles in magma that turn below the bottom of the Indian Ocean are less massive than in other places on Earth. The lighter material at that point should make the hole in gravitation.  "Geoid undulation in false color. (International Centre for Global Earth Models/Wikimedia, CC BY 4.0) The impact of the ancient planet. In the time when Earth was young. Cause asymmetry of Earth's gravitational field, because there still is the debris of that impact. But the hole in a gravitational field is harder to explain than regular-looking asymmetry.  Could the r