Deep Learning: Layer Types Slideset
These slides focus on layers of neural networks.
Deep Learning: From Perceptron to Neural Network Slideset
These slides explain what a perceptron is and how a neural network is developed based on perceptrons.
Deep Learning Performance Slideset
These slides give an introduction to the performance of Deep Learning.
ROC Curve Slideset
These slides give an introduction to ROC curves.
Data Science: Online
In this course you will learn the basics of Data Science. Requirements None – The course is suitable for complete beginners. What you’ll learn Data Mining Process (CRISP-DM) Installation of R, and RStudio Package Handling Data Types Control Structures Functions Data Import / Export Data Cleaning Data Filtering Data Reshaping Data Aggregation Working with Times …
Upper Confidence Bound
With this interactive dashboard you will understand how Upper Confidence Bound is working and how the parameters affect the result. Upper confidence bound is a reinforcement learning algorithm that finds a solution to problems with incomplete information or uncertain rewards. It takes its learnings into account for future actions. Assume you go to a casino …
Hierarchical Clustering
In this interactive tutorial you will learn to understand hierarchical clustering. You can modify the number of points, but that won’t be our focus in this tutorial. Let’s use 12 points, just to have a different setup than in the 101 lecture. We will focus on the impact of the parameters “distance metric” and linkage …
Why Multiple trees outperform a single tree
This dashboard teaches you why multiple trees outperform a single decision tree. The data is artificial. There is a diagonal line, separating two classes. All green points are part of class B and are to be found in the upper left triangle. All red points are part of class B and are to be found …
Train / Validation / Test Split
This interactive dashboard will help you to understand train / validation / test splits. You can modify the data count between 10 and 1000. As default I set 60 % training ratio. That leaves 40 % for validation and testing. With the second slider you can set validation ratio. Test ratio is set implicitly, because …