This is the second post in my series about a computer vision project I worked on at SAS. In my previous post, I talked about my initial research and excitement for the project. In this post, I’ll talk about how I refined my goals and got started with the project
Recently, I was given an amazing opportunity to work on a project in biomedical image analytics in collaboration with a large university medical center. The goal of the project was to develop a computer vision system that identifies tumors in CT scans of livers. I have always loved applying technology
Whether you’re applying for your first credit card or shopping for a second home – or anywhere in between – you’ll probably encounter an application process. As part of that process, banks and other lenders use a scorecard to determine your likelihood to pay off that loan. Naturally, this means
What is object detection? Object detection, a subset of computer vision, is an automated method for locating interesting objects in an image with respect to the background. For example, Figure 1 shows two images with objects in the foreground. There is a bird in the left image, while there is a dog
What’s the most important component of analytic analysis? The data? The model? The deployment? Getting the business problem right? All the above? Or does it simply depend on who you ask? While the model gets all the attention, and the data requires most of the effort, there is that step
We have updated our software for improved interpretability since this post was written. For the latest on this topic, read our new series on model-agnostic interpretability. While some machine learning models – like decision trees – are transparent, the majority of models used today – like deep neural networks, random forests, gradient boosting
There are four widely recognized styles of machine learning: supervised, unsupervised, semi-supervised and reinforcement learning. These styles have been discussed in great depth in the literature and are included in most introductory lectures on machine learning algorithms. As a recap, the table below summarizes these styles. For a comprehensive mapping
Deep learning has taken off because organizations of all sizes are capturing a greater variety of data and can mine bigger data, including unstructured data. It’s not just large companies like Amazon, SAS and Google that have access to big data. It’s everywhere. Deep learning needs big data, and now
In machine learning, a feature is another word for an attribute or input, or an independent variable. What is feature engineering? Feature engineering is a process of preparing inputs for machine learning models. The goal of feature engineering is to to improve classification accuracy by considering the limitations of the
Several weeks ago, I wrote about practical advice from a Chief Data Scientist in my blog “From Aristotle to Pi: Practical advice from a chief data scientist.” Now I want to offer my advice as a newbie trying to navigate through machine learning concepts and how to code them. Over
