Influencing People (Essay)
“The creatures outside looked from pig to man, and from man to pig, and from pig to man again; but already it was impossible to say which was which” writes George Orwell in his novella Animal Farm, published in 1945. […]
Tag: Machine learning
My Favorite Papers at COLING’2020
In December 2020 I attended COLING’2020 (the 28th International Conference on Computational Linguistics) to present “Contextual BERT” at the TextGraphs-14 workshop and to learn about the latest advancements in natural language processing (NLP). This year the conference was not held […]
My Favorite Papers at NeurIPS 2019
In December 2019 I had the pleasure to attend the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) in Vancouver, Canada, to present my work on document understanding. During the three main conference days there were a total of […]
Vision-based Page Rank Estimation with Graph Networks
As part of our Bachelor studies, Samed Güner and I worked on a student research project on vision-based page rank estimation. In this blog article we share our work on a non-technical level. The accompanying written report contains all the technical […]
The Role of Artificial Intelligence in Future Technology
“That’s me!” is what world’s leading professional player Lee Sedol from South Korea would have proudly replied to someone asking “Who is the best player at the Chinese game of Go?” – until he was beaten in a five-game match […]
Linear Relationships in the Transformer’s Positional Encoding
In June 2017, Vaswani et al. published the paper “Attention Is All You Need” describing the “Transformer” architecture, which is a purely attention based sequence to sequence model. It can be applied to many tasks, such as language translation and text […]
Using TensorFlow’s Batch Normalization Correctly
Update: This guide applies to TF1. For TF2, use tf.keras.layers.BatchNormalization layer. The TensorFlow library’s layers API contains a function for batch normalization: tf.layers.batch_normalization. It is supposedly as easy to use as all the other tf.layers functions, however, it has some pitfalls. […]
[Paper Recap] Multiple Hypotheses Prediction
The paper Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses was publish by Christian Rupprecht et al. in late 2016. The authors propose a training technique for machine learning models which makes them predict multiple distinct hypotheses. This is an advantage for […]
Timœ Goes By: Verifying the Age Estimator How-Old.net
how-old.net is a project from Microsoft that guesses the age of people on a photo based on their faces. I have tested it with an image that consists of 21 photos. Each photo was taken around the time of my n-th […]