Looking at face recognition where there could be shapes combining eyes, ears, mouth and facial expressions. I wonder.
Could this be used for some sort of fractal version of machine learning. Like the old fractal mountain landscape generator.
My idea is to see if shapes could be used on the output from the weight matrices from the various layers. That is. You have some ?grid like shape that you drag connected lines on. Making the output shape look different.
Change the shape a little and see what happens. What can it be used for?
So this could be a GIMP or Photoshop like layer where you input insert non optimizable parameters. Like colors, contrast, local scaling etc. I think it can be artist preferences.
That is. Easy changeable user input. Like the mountain seed generator where you change a single number.
My Previously Thought To Believe Died Orchid ?urinated All ?Toxins. Just remove the excess water and replace. Looks like this now. 9 fine looking flowers. Could it have implications for almost dead crops?
I think the ?only way to get sustainable rain in the arid desert is to manually water those places which has gotten som rain recently. When the rain hits those places again you will have a ?secondary effect. Then a third.
The idea is that after this the weather ?network would have picked up on the vegetation changes in that place to direct more sustainable natural rain.
We cant eat solar panels but we can eat food and both use the sun for energy. Therefor for our future. For our survival. I believe we need to make smart business opportunities for people. Even if the money invested per person is small.
Food costs a lot for people every day. If they could invest in food production, farming, innovation etc. Then get ?cheaper food. Then we would create a very smart resilient future.
For instance. The deserts could be green with food crops. Its going to cost money in innovation and tech but the planet is worth it. We are going to save it.
From machine learning there is the philosophical possibility to direct data from a later layer back to a previous layer. I call those networks internal loop networks.
Then if everything needs to be computed in some way. Could a magnet calculate its solution from recurrent information. The field lines look like loops so why not. So data and energy goes from one layer to the other along the magnet back to the input and output layer.
So I wonder. Is stored energy just a compressed mass information bundle. I mean. When you compress information you get a higher information density. So why could not energy storage be a compress and decompress process?
I mean. If energy is like the image you are trying to compress. Then decompressing it will restore the energy to its original state.
Its when you tap the decompression process its gets interesting. Since then I assume you get information loss in the image but you can create another image with that energy you withdraw.
So you can manipulate the choice for the decompression process. So energy can be iterated out to create another “image”.
So a black hole just compresses all the mass-information into one ?neat compressed energy bundle. To be decompressed I guess somewhere else for energy.
Could information be stored in a material? I mean if you use an error function as a criterion between steel and plastic. Then maybe random() as input to the material model could make plastic with steel properties.
Something like that could be an abstract version of material design.
For example. If you choose the model() to represent A,b in Ax=b. That is. A,b = model(…). Then use a proper algorithm to calculate x = np.linalg.solve(A,b). The x here is the target value which also have some loss.
Then the idea is that you filter the iteration to always have some truth. You denoise it if you will. The machine learning model can not do all the calculations. Its not intelligent.
I think this can be used with diff equations also. Just let the model represent a system of linear differential equations. Then solve the system with some known algorithm. So the algorithmic solution is done for all iterations.
So the idea is to use algorithms together with the machine learning model to calculate a Linear System Model Of Machine Learning.
Very often the physics simulation in Blender gets a bouncing result. Pieces fly in all directions. So I wonder. If this could be a balancing problem. If so then machine learning have solved similar problems.
Then to improve the solutions I think a denoise_function(solution.reshape(biggest_rectangular_shape),weight=0.0001).reshape(org_shape) in the machine learning loop could be used.
So the idea is to improve the physics simulation in Blender.