# Machine Learning Time Series Idea – From Points To Histograms To Network Object Predictions?

I experimented recently with predicting histograms cutting the time series into slices and learning the histogram for each piece. Then using histogram(i) to histogram(i+1) predictions.

I wonder if the same could be done also with objects like machine learning networks. That is. Predicting the network parameters.

So the idea is to cut the time data into slices. Then I will try experimenting with setting the input as object(slice (i)) and the target as object(slice (i+1)). After training the model. I ?will be able to predict a network model object for a future object with the last object as input.

I probably need objects that does not have so sensitive parameters so it allows for a little error.

# Speculation – If Nothing Is Random To The Universe Then Every Curve Should Make Sense?

I was wondering if you could use machine learning for interpolation. A use of this method could perhaps be to control overfitting.

So you have discrete values in a target data vector. Zeros and ones. My idea here is to find a smart machine learning interpolation such that overfitting is reduced and output of the machine learning network converges to the discrete target values and is able to predict correctly.

Basically the in between interpolation curve should also make sense as well as the target values. Is it possible to give a large network a nudge in the right direction? Fitting for the smart interpolation curve.

# Speculation – Machine Learning Information Experiment

Could information be data that make sense to a network?

So you start with information that makes sense. Some measurement. The target information to a machine learning network model. Then the idea is that you test some input data to see if you got some reasonable accuracy. Then you can say that the input data makes sense to this network. Which is based on sensible information. So the input data is relevant information to a degree which make sense to a network.

I think you can split the information into time information and frequency information ( histogram ). The frequency information is ?always present. Like different distributions that are somewhat predictable throughout the data.

# Machine Learning Idea – Visualize Time Series Loss Where Loss = Loss ( time, iteration )

Just a quick idea.

To see the problematic areas of your training. After the training is done. I guess that it could be good to cut the time series into slices and compare loss for each time slice. It should show where the model has problems and perhaps ways to improve.

Image generated after one epoch. The plot shows different loss for different times of the year. Could it be that summer time has more energy to turn things around. Making a prediction more difficult?

# Startup Site Idea – Python Today

Inspired by www.linuxtoday.com why could we not have something like python today.

The idea is that you are presented with a small list of mini tutorials, news and other python related topics.

Feeling like a little python today ; )

# Machine Learning Idea – Flying Histogram?

Future histogram prediction of a time series.

Come to think of it. Feelings could perhaps be some sort of space localisation histogram.

https://youtu.be/JDgL5hkm4Xg

# Entertainment Idea – Possibilities With Creative Commons Licensed Satellite Channels?

A quick idea.

With solar and electricity getting in the hands of many African families. I wonder what we could do if we had create commons licensed satellite channels.

With this I think its possible to distribute this kind of TV to a wider audience. This over Wifi so they don’t need to be connected to the Internet.

Now that we have electricity from solar I think entertainment could be important as well.

# Aid Idea – NGO’s And Volounteers Helping People Get Employed

The idea is simple.

We have Non-governmental organizations working to aid people. A measure that I think works is getting people a job with an income.

I mean. The innovation capability lays more with the NGO’s not perticulary with the employment service.  To keep the innovation going I think you have to have many groups that can influence each other.

So the idea is that we have NGO’s and volounteers coming up with ideas and measures to get people the employment they need.

# Startup Idea – Raspberry Pi Sense HAT For The Phone?

A quick startup idea.

Many have a raspberry pi but more have just a phone. So why could we not have interesting electronics project products for the phone. I mean here is a ?billion dollar market.

I think you just need a USB connection to program the card from the phone. A blue tooth keyboard could be useful though.

# Mathematical Speculation – Image Based Markov Chains?

I recently found setosa.io . It got a page with an excellent visual explanation of Markov chains.

I guess that Markov chains are just a probability selector among different states. From this I wonder if I could generate some idea.

I wonder if many states together with their probabilities could form a non random image. That could perhaps look like an ocean from top view.

Then with image processing tools I guess it would be possible to enhance that model. Sharpen the image with google super type image resolution and other image tools like noise filters.

So basically. Every parameter cluster of a model should ?perhaps be a non random looking image.

# Product Idea – Using A Solar Air Conditioner For Extracting Water From Air?

I came across the desert twin water producer when search for ”water from air desert”. Hmm. Two parts. This sounds like a two part air conditioner with refigerants.

Viola.

I think you can run an air conditioner on solar power these days. So you have one part for lowering the temperature for water extraction and one for removing heat from the process. Like an air conditioner. The idea was to build something upon availible technology to make it cheaper.

Thanks Google image AI for presenting me this desert twin image and http://sunglacier.nl/desert-twins-in-sahara

# Machine Learning Generalization – Apply Super Resolution To Noise Filtered Weight Matrices ?

By generalization I mean handling more inputs. Then a strategy could be to update the weights so that you get a non random looking image. I think you can do this by applying a noise filter to the matrices.

Then to get a better generalization I wonder if you can apply a Google type super resolution to these weight matrices that now look like images. So with this you have updated the weights based on experiences from many previous images.

If something like this works then you have effectively trained your network with a ?lot of samples you did not have.

# Idea – Could You Construct From Sound Predictions?

In short.

If you sample the audio from machines with better and better efficiency. I assume its then possible to imagine or predict the sound from a slightly better machine using machine learning. Then with this predicted audio sample. Then I wonder. Could you then use this together with other data to construct this slightly better machine with the target audio?

# Product Idea – Dyslexia Reading Tablet?

With the help of AI its possible to record eye movement. I wonder if you can make use of that information in a reading tablet built for those with reading difficulties.

The idea is that you can get different texts and see how well you scored. Then adapt the preferences of the reading tablet so that it suits your needs.

Maybe different apps could emerge that helps people to read.

I think machine learning or AI can serve as inspiration for an app idea of mine. In machine learning you have many additional data to predict your target data.

So an example would be to play audio side notes. This would ensure you can guess the content of what your reading. The audio side notes as additional data to your prediction to the words and letters.

With all these apps and the eye tracking you could see what works for you.

# Idea – Polar Cardinal Directions?

Since we use cardinal directions north, east, south, and west as some kind of position coordinates for places. I wonder if you just can add a fuzzy radial component to this.

So my idea is to split the radial component into something like outer and inner. So with this my town is located north of outer Stockholm. Without the radial component the location would be somewhere in between what considers inner and outer.

# Test – MP3 vs OGG Machine Learning

Conclusion: No bigg difference between MP3 and OGG below ?15kHz. Yeah well just for fun.

Come to think of it. Maybe this can be used as an automatic EQ. Just use pyevolve or “for” to see what EQ setting produces the best sonogram. For the best settings in time for the sample or the best overal setting. Like a dynamic EQ for the whole song.

# Startup Idea – Global Online Education Platform?

Let the primary or secondary students of all over the world learn at their own pace, improve their grades or repeat education.

I think its an idea worth trying.

# High Risk High Reward – Machine Learning Models With Division?

A quick idea.

I assume many functions that machine learning tries to mimic has divisions in them. With division comes to possibility for division by zero. However I think there is a relation between high risk and high reward in machine learning also.

One such reward could be faster convergence.

# Math Idea – Space Time Vector Transformation

A quick idea.

I was wondering. In an hourglass you have a vector like sand beam that forms a cone.

Then could this be inspiration for a transformation for a vector?

# Education Idea – Higher Education Inspired By Kaggle.com

For anybody interested in education check out kaggle.com. Its a social education site for computer science and machine learning. Apart from tutorial project competitions you can learn from discussions on subjects. Pretty good. This is what I would like for university higher education. If you could learn from talented students. We would get much better value for the time and money spent.

The idea is that we could have very effective higher education if we build sites like these for the other subjects.

# Idea – Encode Images As ?Video For Machine Learning Datasets

A quick idea.

I tought I try an Udacity course on machine learning. However the notMNIST_large contained over 200 000 files so it kind of broke my phone.

From this I got the idea to video compress the images to ten files corresponding to thousands of images from the letter A to J.

I think you can extract the images with some python module. The important thing is that this reduces 200 000 files down to 10. Which is much more friendly.

Another idea would be to quickly view the image set. Just play it as a video in mpv.

The size from the default settings got it down to just about half the size. To my surprice. But .png compression is pretty good.

https://youtu.be/00p7aaQqHZs

# Biology Idea – Kinship Mimicry

Here is my take on imperfect mimicry. I wonder if there are such a thing as imperfect mimicry.

If you take evolution into a count then the specie might just give the illusion that they are a closely related to the dangerous specie.

An example would be a bird coming to a different island where the wasps look a bit different in terms of size, shape or more. The wasps would probably keep some similarity which would not cost so much in terms of performance, like the color of a car.

So, perfect mimicry is not necessary. The specie just has to fool the predator that it is related.

I think it should be called kinship mimicry, not imperfect.

https://en.wikipedia.org/wiki/Mimicry

// Per Lindholm may 2014

# Phone Idea – Build Your Own Wifi Compute Stick

My phone has double the number of cores (8) of my stationary computer and it was still much more affordable. This might be the case for some future to come. The phone being a device people buy a lot of. Drops in price much faster and you can afford higher speeds.

So here you can create your own smartphone wifi connected compute stick.

What you need is the android app Termux and some googeling. A repository is available for termux which enables you to install gcc, numpy, scipy of the latest versions. This for jupyter notebook. A web app that lets you connect on the internal wifi network to your phone from a web browser on your slow computer.

I installed via pip the latest keras with theano and sklearn. Great for novice users in machine learning.

With this you could enable fast computing with old CRT screen computers, raspberry pi and the like.

Below I connected the phone computing device with USB internet sharing. Typed arp in the command window to get the ip of the phone. Plugged that ip:8888 in chromium browser. You need to enable ‘*’ all ip in jupyter config.

# Phone Coding Idea – Python Machine Learning via Android App Termux and pip (sklearn, keras)

With an external keyboard you can get started with machine learning on the phone. The procedure is not perfect. But I attached some screenshots. The main app to use is Termux. It does not hog the cpu as much or not at all.

For termux you need the  “pointless” repository that installs gcc, scipy and numpy. The rest can be installed by pip.

DONT run all cpu cores on the phone. My phone (8 cores) overheated temporarily shutting own one core. However this is probably not healthy for the phone.

You can limit the number of used cores by limiting numpy, see screenshot. I limited it to just two cores. I ran some test for keras using theano as the backend. I also got sklearn installed from pip.

You can use pip to install jupyter. It installs a http server app you then access from the regular android webbrowser “localhost:8888”.

With this I think you can follow some online courses on machine learning that does not use the GPU.