Why my first job in data science was not what I expected — New shirt, new shoes. I was ready for my first job in one of Ireland’s biggest banks. I was excited. Looking back, I had good reason to be. I was able to work on impactful projects and I learned an immense amount. In fact, the biggest lesson was: Data science…

How to incorporate the scientific process in your data science analysis — Business science, sports science, food science… we love throwing the word science behind other words. It makes those fields sound, well, more scientific. Yet, if we are not careful they will have more in common with pseudoscience. Data science is no different. On the surface, it may seem close to…

The intuition, maths and code (R and Python) behind partial dependence plots and individual conditional expectation plots — Both PDPs and ICE plots can help us understand how our models make predictions. Using PDPs we can visualise the relationship between model features and the target variable. They can tell us if a relationship is linear, non-linear or if there is no relationship. Similarly, ICE Plots can be used…

Doing an exploratory fairness analysis and measuring fairness using equal opportunity, equalized odds and disparate impact — It is no longer enough to build models that make accurate predictions. We also need to make sure that those predictions are fair. Doing so will reduce the harm of biased predictions. As a result, you will go a long way in building trust in your AI systems. …

How to effectively run and debug code in a resource-constrained environment — Queue job, wait 24 hours, cuda runtime error: out of memory Queue job, wait 24 hours, FileNotFoundError: No such file or directory Queue job, wait 24 hours, RuntimeError: stack expects each tensor… AHHHGH!!! Debugging code on a high-performance computing (HPC) cluster can be incredibly frustrating. To make matters worse, at…

Build an object detection model, compare it to intensity thresholds, evaluate it and explain it using DeepSHAP — If the world was less chaotic self-driving cars would be simple. But it’s not. To avoid serious harm, AI has to consider many variables — speed limits, traffic and obstacles in the road (such as a distracted human). …

Look to past projects, things you want to learn about and your professional and personal experience — It was March 2020. Need I say more? I found myself alone, in a foreign country and confined to a 5km radius. I had absolutely nothing to do. On the brink of insanity, I decided to do something I always thought about — write an article online. That first article…

How skip connections allow CNNs to perform accurate semantic segmentation with less data — U-Net is a popular deep-learning architecture for semantic segmentation. Originally developed for medical images, it had great success in this field. But, that was only the beginning! From satellite images to handwritten characters, the architecture has improved performance on a range of data types. …

How understanding your model can lead to trust, knowledge and better performance in production — We seem to be in the golden era of AI. Every week there is a new service that can do anything from creating short stories to original images. These innovations are powered by machine learning. We use powerful computers and vast amounts of data to train these models. …