This article is a the next part of the “Hello ML.NET” article. After reading this article you will be able produce a ML.NET model that estimates how long video encoding will take based on the video’s properties. You will learn to work with various datatypes and preform data wrangling to prepare data for model training and evaluation.
To start off, lets take a look into how ML.NET treats data.
This section is a overview of the documentation found here, as well as my observations while working with ML.NET
IDataViewis the data pipeline machinery for ML.NET, Other components of…
This article is a the next part of the “ML (.NET) concepts for developers” article. This article will use the iris dataset to create a ml model that predicts its species based on the measurement of its features.
To start off with, the 3 main architectural concepts of the ML.NET architecture is explored.
In ML.NET there are 3 main components:
IDataViewhas a schema
This article is a the next part of the “Basics of ML.NET for developers” article. Concepts discussed here is mostly generic however it makes several callouts to ML.NET package.
Artificial Intelligence (AI) Any method that allows computers to simulate human-like intelligence. This includes machine learning, fuzzy logic, genetic algorithms.
Machine learning (ML)
Is algorithms and statistical models that extract patterns from data to preform tasks without explicit instructions.
Deep Learning (DL)
Is a subset of ML, focusing on artificial neural networks with more than 1 hidden layer
A typical machine learning project will have the following components…
ML.NET is Microsoft’s answer for a machine learning package that runs on the .NET ecosystem. Once one gets used to the package, it is easy to develop and deploy custom machine learning models in .NET based applications.
ML.NET is not like other (non .NET) machine learning packages therefore it is important to understand its unique quarks before diving into development. If this is your first exposure to machine learning then you need to keep in mind that other machine learning packages don't behave like ML.NET.
Please note this article is written for developers who are new to the world of…
The Occupy movement, in 2011, saw protests around the globe raise awareness for the growing inequality between the rich and poor. It led to the income inequality take center stage on the political field and has had direct, and indirect, impact on policy and politics over the last decade.
Fast forward to 2020, George Floyd’s death at the hands of a police officer has sparked a new wave of protests that put systemic racism, police brutality, and inequality faced by African Americans in the spotlight. …
A growing population, climate change, and other factors require us to produce more food with less land. A 2018 study has shown that it would require a landmass the size of Canada if everyone on Earth were to be fed to a healthy level . The 2018 World Resources Report has found that we will need to produce 58% more food by 2050 to keep up with current trends in demand . Agriculture currently uses around 50% of the Earth’s surface , an additional 600 million hectares (6% of global landmass) of land will be required to meet future demands…
Have you ever been in a situation where you repeatedly change a value? Perhaps you found yourself changing the number of clusters, subsetting a % of data or just limiting axis on a chart.
Jupyter Notebooks have a range of widgets to make these kinds of changes more user-friendly, aesthetically pleasing, and intuitive. In addition to all these benefits, you will also learn UI concepts and test code that handles user input. Let’s explore some essential user inputs.
This article will focus on using the ipywidgets package to handle user input; each input element is considered to be a widget.
These days artificial intelligence, machine learning, and data science (or anything related to ‘data’) seem to be thrown around a lot. It is crucial to be able to work cooperatively and communicate with data personal to ensure you get the best outcome.
The chances are there is a probably a data team in your organisation, if not there most definitely is one in your industry. Let’s start at the root, so what is data anyway?
In the most basic form, data is any unit of information. In fact, by reading this article, you are producing data. Anything and everything that…
The Mandelbrot set, named after mathematician Benoît Mandelbrot, is an example of a fractal in mathematics. The Mandelbrot set is important in chaos theory and it was one of the first examples of a simple formula creating complexity. Benoît Mandelbrot first observed the set when he used IBM’s newly developed computers to visualise mathematical formulas in the 70s. There is a great writeup on the history for fractals here: https://www.ibm.com/ibm/history/ibm100/us/en/icons/fractal/
Calculating and visualising the Mandelbrot set takes a significant bit of computing power, in this article I will present some code that can take full advantage of your computer’s resources…
The EcoDunio kit by DFRobot is a sets up an automatic watering system for people who want a more hands off approach to growing plants. While this setup is possible with an Arduino and associated sensors, the EcoDunio kit packages it up with an Atmega32U4 microcontroller and all the components you will need to get a system up and running smoothly.
Unfortunately, the kit’s documentation and code seems to have been neglected and need to be updated for clarity and compatibility. In this guide I will run through how to get the EcoDunio up and running.
You will need: