Digests » 4
this week's favorite
In recent years, the t-distributed Stochastic Neighbor Embedding (tSNE) algorithm has become one of the most used and insightful techniques for exploratory data analysis of high-dimensional data. Used to interpret deep neural network outputs in tools such as the TensorFlow Embedding Projector and TensorBoard, a powerful feature of tSNE is that it reveals clusters of high-dimensional data points at different scales while requiring only minimal tuning of its parameters.
Being a high schooler myself and having studied Machine Learning and Artificial Intelligence for a year now, I believe that there fails to exist a learning path in this field for High School students. This is my attempt to create one.
This video gives an overview over a project I've developed for the "Visualization 2" Lecture from the Visual Computer Masters program at TU Vienna, aiming at supporting the explanation of Convolutional Neural Networks with interactive visualization.
This post describes how to setup a Conditional DC-GAN to generate images from all the classes of CIFAR-10 data.
Implementation of SeamCarving method that allow to remove an object from a photo.