I wonder if water. Being essential to life. Also is optimized for life. Even if life has evolved in relation to water. The other way sounds probable also.
I read that there can exist para- and ortho-water. From a philosophical point of view. It could make sense to separate properties of water if there exist a smart solution found with complex combinations. Like a pattern of ones and zeros.
Then these combinations would have to be computed/learned through ?millions of years. If so then splitting water is always a bad idea. You ?risk loosing properties that is needed for life.
Then could there exist a short circuit machine learning based processor that either has learned the most common ways to solve a short circuit or iterate a fast solution. Mobiles to Self Driving Electric Cars??
Constructive forces can make something. But like in a ?GAN machine learning network you need a discriminator force to shape it into something good. A destructive force. So I wonder. Could this be made into an engineering technique of some kind. For instance. Could it work for a fatigue engineering problems?
I mean. I think GAN networks produce the most advanced type of images. So it ?could work for producing fatigue predictions.
Similar To F-Droid. Could we have a Refugee Android App Repository? For supporting apps made by refugee.
My woman came up with this idea. I got sick today.
But if you want you can translate an image of a typical trashcan from an AI point of view. It could be like. Circular opening black trashcan.
Then you have something to innovate with. So perhaps you get narrow rectangular opening trashcan. That can be made from a plastic/paper shopping bag.
I think one problem with deep learning is that if you add an ?odd looking training sample to the model(). Then it could ?perhaps deflect a little. Give off a little on the prediction accuracy.
So the idea is to check what the response new samples have on the already learned samples. Maybe its possible to have a system that senses deflection in the weights. One idea would be split the problem into two units and so on? Something similar to cells?
Basically you encode the labels with the error correcting fomula. Like the Hamming Code. Just google ecc error correcting code.
Then train. On the test set you can then verify a little that the classification is correct by computing the three parity bits from the data and compare. It should also be possible to correct a classification.
Here I got a data bit error . 4 bits index [0,1,2,4] were data bits. The other 3 were parity bits.
The correct was y_test.