Recent Posts

Detecting objects using segmentation

3 minute read

To find objects in images, one normally predicts four values: two coordinates, width and height. However, it is also possible to formulate object detection a...

Losses for Image Segmentation

7 minute read

In this post, I will implement some of the most common losses for image segmentation in Keras/TensorFlow. I will only consider the case of two classes (i.e. ...

n-gram, entropy and entropy rate

5 minute read

n-gram models find use in many areas of computer science, but are often only explained in the context of natural language processing (NLP). In this post, I w...

Deriving and implementing LDA

3 minute read

In this post, I will derive and implement Linear Discriminant Analysis (LDA). See also chapter 4.3 in [1].

Avoiding underflows in Gaussian Naive Bayes

1 minute read

There are mainly two ways to avoid numerical instability when implementing Gaussian Naive Bayes (GNB). Either one applies the log-sum-exp trick or one takes ...