Data Science Austria

Latest News about

Featured

How to assess a binary Logistic Regressor with scikit-learn

Functionality Overview Logistic Regression is a valuable classifier for its interpretability. This code snippet provides a cut-and-paste function that displays the metrics that matter when logistic regression is used for binary classification problems. Everything here is provided by scikit-learn already, but can be time consuming and repetitive to manually call

How do Graph Neural Networks Work?

Graph neural networks (GNNs) have emerged as an interesting application to a variety of problems. The most pronounced is in the field of chemistry and molecular biology. An example of the impact in this field is DeepChem, a pythonic library that makes use of GNNs. But how exactly do they

You said ‘smart devices’, really?

We saw in the previous article that experts don’t always agree on definitions, and we tried to clarify the confusion around the Internet of Things (IoT). Let’s dig deeper now and discuss the “smartness” of a device. Everyone knows what a smartphone is, but how smart is it? And what

The Complete Guide to Decision Trees

Everything you need to know about a top algorithm in Machine Learning Photo by Helena Hertz on Unsplash In the beginning, learning Machine Learning (ML) can be intimidating. Terms like “Gradient Descent”, “Latent Dirichlet Allocation” or “Convolutional Layer” can scare lots of people. But there are friendly ways of getting into the

X-AI, Black Boxes and Crystal Balls

Inside AI The Road to Trusted AI On our road to trusted AI, I discussed in my previous blog the question of bias, how it travels from humans to machines, how it is amplified by AI applications, the impacts in the real world, for individuals and for businesses, and the importance

Unsupervised Learning: Dimensionality Reduction

Compress features, reduce overfitting and noise and increase eficciency and performance Introduction As stated in previous articles, unsupervised learning refers to a kind of machine learning algorithms and techniques that are trained and fed with unlabeled data. In other words, we do not know the correct solutions or the values

AI won’t replace artists- instead, it will augment them

In an unsurprising yet exhausting twist, the art world is obsessed with works created by artificial intelligence. If you’ve been keeping up with art news, you’ll know that last October a very generic AI portrait sold for a cool $432,000. It was made by an open-source program called GAN. Christie’s

Are neural nets close to producing real art?

Neural nets are a type of algorithm — a process that takes in information, processes it somehow, and produces output. In my opinion, they are the source of the most amazing results in artificial intelligence and machine learning today. Versions of these algorithms have already been designed to complete tasks previously thought

Data version control with DVC. What do the authors have to say?

DataOps is very important in data science, and that my opinion is that data scientists should pay more attention to DataOps. It’s the less used feature in data science projects. At the moment we normally are versioning code (with something like Git), and more people and organizations are starting to

Detecting Cute Animals with Machine Learning

Training and building a custom image classifier mobile app Photo by Álvaro Niño on Unsplash When a data scientist colleague of mine recently found out I have a background in mobile app development, he asked me to show him how to use a machine learning model in a mobile app. I figured

Python