Archive

Archive for March, 2020

“Hello World” in #GeneticAlgorithms in C#

maxresdefault

Genetic algoritms are a computational representation of what happens in nature, how evolution solves problems, so it applies a “survival of the fittest” approach to solving a problem.

Like Machine Learning, instead of prescribing the solution to a problem you provide problem examples and corresponding solutions, and let the GA (Genetic Algorithm) try to figure out how to solve that problem.

Like in nature, (If we ignore religion for a moment!), nobody designed a cheetah to run faster than a gazelle, but when presented with a problem of a fast gazelle, the solution was to run faster than it. Other solutions, like running backwards, were not effective, and so were not selected for.

So, TL;DR; here is the github repo, which as code in C# using GeneticSharp to solve a very simple problem; https://github.com/infiniteloopltd/geneticAlgorithm_helloWorld

Here, the problem posed is simple addition;

// 1 + 1 = 2
// 2 + 2 = 4
// 3 + 2 = 5

However, you can substitute the parameters with more complex equations, and the GA will still try to solve it, it just will take longer.

The “Genes” of the GA are addition, substration, multiplation, division, and constant numbers (1,2,3). So, it will probably struggle to solve Sin(), Tan(), Cos() etc. Like in the same way that DNA is limited to making protiens, so you can’t make Petrol using DNA.

So, to wrap up this post, here is the code to run a simple equation solver using Genetic Algorithms;

static void Main(string[] args)
{
// Problem: Simple addition
// 1 + 1 = 2
// 2 + 2 = 4
// 3 + 2 = 5
var myInputs = new List<FunctionBuilderInput>
{
new FunctionBuilderInput(new List<double> {1, 1}, 2),
new FunctionBuilderInput(new List<double> {2, 2}, 4),
new FunctionBuilderInput(new List<double> {3, 2}, 5)
};
var myFitness = new FunctionBuilderFitness(myInputs.ToArray());
var myChromosome = new FunctionBuilderChromosome(myFitness.AvailableOperations, 5);
var selection = new EliteSelection();
var crossover = new ThreeParentCrossover();
var mutation = new UniformMutation(true);
var fitness = myFitness;
var chromosome = myChromosome;
var population = new Population(100, 200, chromosome)
{
GenerationStrategy = new PerformanceGenerationStrategy()
};
var ga = new GeneticAlgorithm(population, fitness, selection, crossover, mutation)
{
Termination = new FitnessThresholdTermination(0)
};
ga.GenerationRan += delegate
{
Console.Clear();
var bestChromosome = ga.Population.BestChromosome;
Console.WriteLine(“Generations: {0}”, ga.Population.GenerationsNumber);
Console.WriteLine(“Fitness: {0,10}”, bestChromosome.Fitness);
Console.WriteLine(“Time: {0}”, ga.TimeEvolving);
Console.WriteLine(“Speed (gen/sec): {0:0.0000}”, ga.Population.GenerationsNumber / ga.TimeEvolving.TotalSeconds);
var best = bestChromosome as FunctionBuilderChromosome;
Console.WriteLine(“Function: {0}”, best.BuildFunction());
};
ga.Start();
Console.WriteLine(“Evolved.”);
Console.ReadKey();
}

 

Categories: Uncategorized

Cryptanalysis with #ML.NET (#AI / #ML)

1200px-Mldotnet.svg

Disclaimer: This approach works only when you have a limited-length plaintext, and plenty (millions) of examples of cyphertext / plaintext pairs. I achieved 90%+  accuracy with this approach, it’s not perfect, and requires several days of training (8 hours per character of plaintext)

So, imagine you have a database held in SQL server that holds a list of cyphertext and corresponding plaintext examples – even if you don’t even know the cypher used, you can still use ML.NET as a means of Cryptanalysis. Without knowing the cypher used, you can’t use brute-force as an approach.

What I did – I broke the cyphertext into individual columns – So one column represented one character of the cyphertext, and I did the same with the plaintext, breaking up the plaintext into one column per character.

Then I ran a classification model for 8 hours on 1 million rows of examples, using the ML.NET model builder, providing each column of the cyphertext as the input, and one column at a time of the plaintext as the label (output).

After 8 days, I had 8 different ML.NET models that could decode the cyphertext.

WITHOUT – even knowing what cypher was being used.

RESULT

Categories: Uncategorized

Restoring a cancelled ML.NET trained network #AI #MachineLearning #ML.NET

cancelled

If you’re using the ML.NET VS Add-in to train your models, you may find it really frustrating if the training suddenly cancels itself, or you accidentally cancel it, and if you’re doing an 8 hour train, then this can drive you nuts.

Thankfully, I found the temporary files, that it generates, and you can still use in your code, although it generates about 10 different models per algorithm, so you’ll need to experiment to find the one that works best (typically it’ll be the 9th or 10th)

So, where are the files?

<user>\AppData\Local\Temp\Microsoft.ML.AutoML

Phew!

And how to load them in?, here’s some sample code;

private static ModelOutput Predict(ModelInput input)
{

if (predictionEngine == null)
{
// Create new MLContext
MLContext mlContext = new MLContext();

ITransformer mlModel = mlContext.Model.Load(modelPath, out var modelInputSchema);
predictionEngine = mlContext.Model.CreatePredictionEngine<ModelInput, ModelOutput>(mlModel);
}

// Use model to make prediction on input data
var result = predictionEngine.Predict(input);
return result;
}

Where you statically define the following variables;

private static PredictionEngine<ModelInput, ModelOutput> predictionEngine = null;

private static string modelPath = @””;

modelpath being the ZIP file of the model.

 

 

Categories: Uncategorized

Super-simple way to deal with non-www #CNAME in #DNS

www-VS-non-www

If you ever needed to point your domain at a external hosting provider, Blogger.com is a good example of this, and you suddenly find that the non-www version of your domain doesn’t work?

Back-up for a second, What is non-www?

non-www is your domain name without the “www” at the start. So “http://MyWebsite.com&#8221; is the non-www and “http://www.MyWebsite.com” is the with-www

If you use Blogger.com to host your blog, then you are told to use a CNAME DNS record to point your “www” domain to ghs.google.com , but you can’t set a CNAME on the “@” record (non-www”), and if you try guessing the IP, then you’ll end up breaking it.

TL DR; Want the solution already?

Just add an A record for “@” and point it to IP address 176.105.255.48 , this server will automatically redirect anything that lands there to the “www” version of the same domain.

If you want to take this further, and would like to explore more about hosting websites on your own domain, then take a look at domaindeflect.com

And for people who are techie, or paranoid, the tiny script used to do this is open source on github, here https://github.com/infiniteloopltd/nonwww

 

Categories: Uncategorized

Using #MachineLearning to predict the age of a #VIN

This slideshow requires JavaScript.

TLDR; Source code for this is available on github here; https://github.com/infiniteloopltd/VinAge

This is a first working example of something useful that I’ve created with Microsoft’s ML.NET framework.

I’ve used the “Issue Classification” scenario, training the model on 10,000 known VIN’s and known ages, and then tested it against a VIN that wasn’t in the training data, and it successfully got the age.

It didn’t work so well on a US VIN, but I guess there needs to be more variation in the training data. Also, it took about 1 second per 100 rows to train, so I can imagine some overnight training sessions!

Antipatterns:

I had also tried this on a “Price prediction” scenario, but it gave quite innacurate results, even though the training only took 30 mins over 6 million rows.

Categories: Uncategorized

Norwegian #VIN number #API (open source)

unr

This website https://www.understellsnummer.com/(or in english here; https://www.understellsnummer.com/en.html) allows you to enter the VIN number of a norwegian vehicle, and search for details about it.

It’s not a VIN decoder, it looks up the exact vehicle in a database of over 10 million vehicles registered in Norway, which is what is used behind the norwegian version of our vehicle registration number lookup here; http://no.registreringsnummerapi.com/

The data comes from official governement sources in Norway, and is updated regularly.

 

 

Categories: Uncategorized

Newly launched #Udemy course for Microsoft #SQL server.

This is my first Udemy course that I’ve published. It teaches you pretty much all I know about SQL server in 6 hours of videos, right from absolute beginner, to expert.

If you’re interested in finding out more about the course, please click the link below;

https://www.udemy.com/course/sql_server/?referralCode=8FFD23693EFA04445F99

If you ask nicely, I have a limted number of coupons available, if you contact me personally.

Here are the course contents;

Microsoft SQL server is the most popular database platform for Windows, and with this course, we will take you from absolute beginner to expert in just under six hours of hands-on experience.

We begin by teaching you how to install your own free copy of SQL server on your own machine, or if you prefer, to host SQL server on the cloud with Amazon Web Services or Microsoft Azure.

Following on, we teach you how to create tables, insert rows, update and delete them, and read them back. You’ll quickly learn how to write queries to filter and sort data, to group and summarize data, to run statistical queries on the data.

Once you’ve mastered the basics, we show you how to create database triggers, to manage transactions, and how to wrap up complex code as simpler code using stored procedures and user defined functions.

But, it’s not all about database development, we also teach you about database adminstration, how to backup and restore your database, and more importantly, transfer your backups to the cloud, like AWS S3 or Azure Blob storage.

We also teach you about database tuning, how to make your queries run faster, and make your system more performant, and about database security, how to protect your data, and comply with data protection laws like GDPR and CCPA.

And to wrap up, we teach you how to connect to SQL server from four different programming languages, Microsoft C# .NET Core, Node JS, Python and Java.

What you’ll learn

  • Students will learn how to use the Microsoft SQL server database platform

Are there any course requirements or prerequisites?

  • Students will require a Windows PC that meets the minimum specifications for installing Microsoft SQL server

Who this course is for:

  • Students interested in learning about the Microsoft SQL server database platform

 

Categories: Uncategorized