Timo Denk's Blog

Science, Programming, 3D-Printing, Music, Philosophy, and More…

Tag: Neural network

Five Years With Neural Networks and a Research Retreat

Five years ago I worked on a project trying to replace a physical keyboard with a glove that was equipped with accelerometers. The idea was to measure the fingers’ accelerations and determine the intended “key press” even though the user […]

April 20, 2022April 20, 2022by Timo Denk

My Favorite Papers at NeurIPS 2021

In December 2021 I had to pleasure to attended NeurIPS (the thirty-fifth Conference on Neural Information Processing Systems). For the second time the conference was held remotely, not in Sydney as originally planned. A total of 2334 papers were accepted […]

December 10, 2021December 23, 2021by Timo Denk

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 […]

December 18, 2019April 18, 2020by Timo Denk

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 […]

May 25, 2019by Timo Denk

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 […]

January 22, 2019January 22, 2019by Timo Denk

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. […]

October 14, 2018May 28, 2020by Timo Denk

[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 […]

October 5, 2017July 3, 2020by Timo Denk

Find posts

About

Hi there! This blog is run by me, Timo. I am a Software Engineer living in Zürich, Switzerland. Please visit my portfolio website for more detailed information.

Editor’s choice

If you just came here and do not know where to go, I recommend looking into these posts:

  • Digit Span Test (most viewed)
  • Cubic Spline Interpolation (math-heavy)
  • Commute Time Tracking (nice read)
  • Linear Relationships in the Transformer’s Positional Encoding (machine learning)
  • Corsairs3D (pirate game – arrr!)

Archive

The archive page of this blog lists all posts in chronological order.

Email Newsletter

There is an email newsletter available. Once signed up, you will receive an email every time a new post is published. That is usually about once or twice a month.

Tags

3D 3D printing Arduino Art Blender Book C++ Car Computer Science Conference Convolutional network Deep learning DenkDevelopment Ender 3 Pro Graph Hardware Haskell Historic History JavaScript Library Low-level Machine learning Math Microcontroller Miniature Modeling Music Neural network Node.js Painting Paper Philosophy Physics Piano Poker Programming Raspberry Pi SAP Science Space Telegram Telegram bot Test Tools

Navigation

Home · Contact · Legal
Proudly powered by WordPress | Theme: Sin by vsFish.

Cookies

This site uses cookies. More