Latest
-
Model Evaluation: Why Accuracy Isn’t Enough
Suppose we have a model that predicts the colour of a ball. We have 5 red balls and 5 blue balls and we ask our model to make a prediction of the colour of each of them. How can we evaluate our model’s success? One approach would be to count the number of predictions that our model gets right. We count the number of red balls that the model predicts to be red (number of True Positives) and count the number of blue balls that our model predicts to be blue (the number of True Negatives). Read Moreâž”
Popular Categories
Featured Articles
-
From Love to Logic: How Algorithms Decide Our Matches
You’ve swiped through dozens of profiles, but why does it feel like there’s no perfect match for you? What if… Read More âž”
-
The Bridges of Königsberg
The sun dipped low over the bustling City of Königsberg, casting golden reflections over the Pregel River. Its waters divided… Read More âž”
-
Information at a Glance: Do Your Charts Suck?
Let’s face it: that report you worked on — nobody’s actually going to read it. In the best-case scenario, people might skim… Read More âž”
-
What if an Infinite Number of Spaceships Arrive at Hilbert’s Hotel?
Suppose you’ve just been hired as the new manager of Hilbert’s Infinite Hotel. On your first day, you arrive at… Read More âž”
-
Python Chess: Game Simulation and Illegal Moves
This is exciting! We’re nearly ready to start simulating a whole game of Chess. There’s just a few more components… Read More âž”
-
Image Segmentation With K-Means Clustering
Looking at the images above, we see an example of an image posterization filter that gives images a cartoon-like appearance,… Read More âž”