Why I Love Keras and Why You Should Too
I started working with Deep Learning (DL) in the 2016 – 2017 time frame when the framework ecosystem was much more diverse and fragmented than it is today. Theano was the gold standard at the time, Tensorflow had just been released, and DeepLearning4j was still being built. Both Theano... Read more
Responsible Data Science & AI – Challenges and First Steps Towards a Practical Implementation
After major incidents, such as the Cambridge Analytica scandal and the alleged racial bias in the COMPAS system that assessed potential recidivism risk in the US, the call for responsible data science & AI frameworks increased. Books as weapons of math destruction, the black box society, automating inequality, and... Read more
The Fashion Industry is Impactful – Let’s Make it Positive With AI
Want to know how you can contribute to a sustainable clothing industry? Listen to my talk at ODSC Europe 2020, “Sustainable Retail Through Open Source, Scraping and NLP,” and take action right away! Pollution, bad working conditions, and animal welfare are topics that are often pushed away by profit.... Read more
Could Your Machine Learning Model Survive the Crisis: Monitoring, Diagnosis, and Mitigation Part 1
As the world is changing rapidly around us, it is often questionable whether something we learned from the past is still valid. Machine learning models that make predictions of the future based on past data points are probably under most scrutiny from businesses in the current climate. Close monitoring... Read more
Building a Production-Level Data Pipeline Using Kedro
Suppose you are a self-taught data scientist who does not have much experience in software development. One morning, your senior executive asks you to provide an ad-hoc analysis – perks of the job, and when you do, she thanks you for delivering useful insights for her planning. Great! Three... Read more
From Good to Great: The 5 Skills You Need to Shine in Data Science
Almost three years ago, I switched from a career in academia to a career in business in a data science role. This used to be somewhat of a rare event, but today it is commonplace: not only is there a shortage of data scientists, but also people change careers... Read more
How to Explain Your ML Models?
Explainability in machine learning (ML) and artificial intelligence (AI) is becoming increasingly important. With the increased demand for explanations and the number of new approaches out there, it could be difficult to know where to start. In this post, we will get hands-on experience in explaining an ML model... Read more
Autograd is PyTorch’s automatic differentiation package. Thanks to it, we don’t need to worry about partial derivatives, chain rule, or anything like it. To illustrate how it works, let’s say we’re trying to fit a simple linear regression with a single feature x, using Mean Squared Error (MSE) as... Read more
Be or Not to be an Anomaly?
An outlier may be defined as an object that is out of ordinary, which differs significantly from the norm. In day to day examples, it could be a baby panda among adult pandas, a champion breaking a world record, or fraud emails in your inbox. Why even bother to... Read more
Continuous Delivery for Machine Learning
Why is bringing machine learning code into production hard? Machine Learning applications are becoming popular in all industries, however, the process for developing, deploying, and continuously improving them is more complex compared to more traditional software, such as a web service or a mobile application. They are subject to... Read more