Monthly Archives: July 2018

Physics Speculation – Inverse Reasoning. Singularities As A Energy Storages. High Amplitude

You split a problem to solve it more easily. Therefor I wonder if the  universe is really a big energy problem. Splitted into many small solvable objects. I mean. Would this mean it stores energy in many small singularities. Since a singularities could have high value. Like divided by zero. This would be a managable way to store lots of energy in a safe way.

So the problem of the universe is safe energy storage?

Machine Learning Innovation? – Sort Data Into Multiple Model Groups From The Model With The Best Confidence. Triangle Model System.

I wonder if this learning technique could work. The idea is to split the data into two or more model() groups. Each belonging to a separate model().

So the way I would test this would be to look at some sort of ?confidence score for each classification the two models could do. Like in the long vector binary encoding. Where you want 1.0 and the rest to be zeros.

So then the idea is to move the sample data into the model group with the highest confidence. This way the two models compete to have data in its group.

Then if I get 100% confidence for each model for training data within its group. Then the sample data transformation output from the test set would be selected from the model with the highest confidence score.

My first try (jupyter notebook) Sort Data into Model() Groups

98.11% Accuracy score

Impressive Feature – Using Machine Learning Super Resolution ( Down Scaled Images ) To Fix Blurry Images ( a little )

I managed to fix some photos that were blurry simply using a super resolution machine learning algorithm.

The idea is simple. Down scale the photo. Until you don’t see the blurriness. Then apply super resolution. Its as simple as that. The result is not any way perfect but its better.

Super resolution should be in gimp I think.

Video Or Image Compression Idea – Example. Optional JPEG Algorithm + Machine Learning Blockiness Layer Removal

Since machine learned super-resolution worked. Why should not do the same training for images with visible blockiness.

The idea is to degrade or hard compress images using some image compression algorithm to blockiness level. Use those images as the training and then as the target use the original images.

If this works than it would be possible to compress images to near ?the maximum.

The maximum ?would be unsupervised labeling of small objects in the image to text form and then machine learning to imagine what the image would look like.

So now you have a machine learning layer on top of chosen algorithm.

Perhaps this could work on youtube also. It would be possible to compress video on quality, not just on resolution. Then use the machine learning layer to correct the blockiness and resolution.

I think this is the way to do it. You have a standard algorithm in the back and a machine learning layer on top of it.

Inventions Idea – Online Volunteer Engineering – Then Order A Prototype Online

As the weather gets very hot. One invention that is missing is an air cooling device. Run by solar. Small enough that it does not cost that much.

For such climate inventions to be built I wonder if we need to connect engineers online.

So the idea is for an online engineer volunteering site with connected online prototype manufacturing site.

Just because we need it.

Machine Learning Idea – Server Heat Dependent On The Type Of Layer Used? LSTM

I wonder. My little laptop goes super hot every time I use something like LSTM. I guess it could be the cache. However. For many processors in a room this could make a substantial difference I guess.

So the idea is for optimize algorithms with machine learning for low energy consumption or heat dissipation. Could there be a “lagom” speed for the amount of heat?

Physics Guess – 3 Body Problem – Non Deterministic Drive?

Just a quick speculation.

Thinking about three-body problems. Since we got earth, the moon and the sun as a three-body problem. I wonder.

Is the three-body problem physics-information important? Is it used as a feature in the universe?

“Unlike two-body problems, there is no general closed-form solution for every condition, and numerical methods are needed to solve these problems.”-wikipedia

Could this mean that the problem is close to non exact? Could this mean there is room for decisions making network for positions and velocity. I mean could the network choose.

Not familiar with the uncertainty principle but it is ?solved by letting a network choose. Kinda the same thing here. Could I guess be similar to my decision numbers. The problem of dividing an odd number into two. Where you have to choose which pile to get one more.

Towards Understanding Fundamental Forces – Fastmem vs Slowmem or Different Decision Making Time

The idea is simple.

Since networks can handle difficult tasks. Networks are probably used everywhere in the universe. Field lines could with a little imagination look like a part of a network.

Therefor I wonder. Why do we have field lines? What sense do they make to a network. If they are used for information. Then a memory is needed. Then what type of memory?

From our own computer innovations we got different memory chips and speeds. Therefor I guess that an atom with its electric field needs fast information to keep itself in shape. Information is what was missing in physics equations.

Where as a gravitational field. There is more time for atom decision making. So a slower information update.

So maybe the force could be responsible for the acceleration of information ( the little mass ). With this I get a strong force where information might need to be updated quickly.

Machine Learning Physics Guess – Water Desert Evaporation?

The idea is simple.

Since sand is made for digging. A probable universe invention would be sand shapes. So I imagine water in the desert would optimize its ground shape and sides. To prevent too much evaporation. To support life.

Looking at pictures of desert lakes. Pretty much everything I see I think are optimized but also perhaps it can take advantage of gravity from the water network.

Machine Learning For Education Idea – Generator Discriminator Network For Sentences?

A quick idea

Say you have some small number of sentences describing an idea. Rewrite the idea a couple of times. This will give me a small set of the same idea. Just written in different ways.

Then the plan is to generate the idea in a text-form. From a Discriminator and Generator network.

So you finally have D(G(input)) == True after ?many iterations.

My goal is to find an idea re-writer for hard to understand topics. The generator will output many versions of the text. You just need to understand one.

Maybe it is as easy as using similar words from a dictionary but with some special fitting.

Machine Learning Physics Guess – Mass Gravity Of Networks – Controlled Attraction And Separation

Since networks can be build by mass and mass is the building blocks of the universe. I wonder. Do all laws containing mass also contain a network?

Then why not include the network in the equations. Gravity for example then ?becomes a more detailed law.

From this I guess that ?antimatter ?being another type of network would not interact gravitationally with matter. ?Since of annihilation. It would not be optimized for life. The gravitation result solution from a network ?can I guess be what is most suitable.

How would antimatter and matter ever separated in a safe way?

Machine Learning Water Network – Tree Roots – Many Functions – Assume A Network

Why does a root system look like the way it does? What other functions does it have other than getting water from the soil?

Since a tree could withstand high winds. I wonder. Could the root system also handle stability. Does it sense gravity?

Whenever there many functions to handle I assume a network. Since complex ability is what networks are for. Therefor I guess the root system is a physical water network.

The philosophical interesting part is that water in tree roots. Are water separated. That is. Separated water is not a ?common configuration. So inventions based on that should not be in the set of probable inventions.

Another water network would be water between rocks.

Pavement Innovation Needed – Look ma I created a bird bath!

This is my limited understanding of the weather network.

Pavement is not life optimized. So what can the sun do?. What parameters do the weather network have that can affect the pavement.

I guess its increases the heat. To create cracks.

Together with the rain it has now created a simple birdbath.

This is what I mean. Things are the way they are since nature needs to optimize for life. Or life would not exist.

So one idea to hold down the temperature on the pavement over time would be for us humans to optimize the surrounding for life. Why not a close by bird bath?

Physics Guess – Light Propagation By Random Cluster And Near Impact Decision Making For Function

A quick idea.

If everything is smart. So should light also be smart.

This make me guess that light propagation is a cluster of randomly located photons. Why. Since it make sense to a network. That is. At near impact the light can make a decision from a formed interconnected network.

The decision could be to optimize the problem for better chances of for life.

So in a sense its a deep end connected network.