Blog

Writing about AI, side projects, and things I find interesting.
Previously known as Pinch of Intelligence.

Three months of agentic coding - my experience

Last month I wrote my experience with AI-generated coding on this blog. I got a lot of positive feedback, so I created another chart for my work up till this month and wrote down the thoughts I had.

All posts

Tokidoki - practice Japanese grammar

I am trying to learn Japanese. This is extremely hard, especially the grammar. I now made a tool to help you practice!

Two months as a vibe coder

The last two months my work completely changed. My job changed from thinking long and hard about problems and coming up with the best few code to solve this, to full-on talking in English to my...

GPT stemt D66/GroenLinks/PVDA!

De verkiezingen komen eraan, en dus zijn er weer meerdere kieswijzers online. Nu we allemaal liever praten met ChatGPT in plaats van met onze vrienden in discussie gaan vroeg ik me af: wat zou...

October 26, 2023

Building a Pikachu Tesla Coil

This week I made a new project: a Tesla-coil powered Pikachu It’s essentially a 3D printed pikachu which emits sparks. What’s cool about it is that I can also play the pokemon theme tune through it...

August 30, 2023

Being a “Top Programming Voice on LinkedIn”

Looks like LinkedIn awarded me a “Top Programming Voice” badge. Although I am always quite vocal about the field of programming and machine learning I earned this badge by copy-pasting a single quote:

Dataset in a Day

How to efficiently create a machine learning dataset in a day — originally published on the Bumble Tech blog.

January 1, 2023

Point and Snap for my smart home

Having smart devices in your home is fun, but turning them off is still a hassle. Taking an app, talking to Alexa, or pressing a button all takes too much time. Why can’t we in 2022 just point at a...

Winning the Edge AnnotationZ Challenge

How the Kognic team won the Edge AnnotationZ challenge — originally published on the Kognic blog.

January 1, 2022

Unit Testing Your Perception System

How to apply unit testing principles to perception systems in autonomous driving — originally published on the Kognic blog.

January 1, 2022

Analysing my swim stroke

Recently I tried to improve my swimming skills. I’m trying to get better at longer distances, swimming with less effort, and going a bit faster. In some videos they talked about optimising the amount...

Landing the perseverance rover on mars

This week the perseverance rover landed on mars A big congratulations for everyone at NASA who made this possible It’s a stunning engineering feat which I followed closely on Youtube. Something I...

February 25, 2021

Sending a Neural Network to the Moon

Sending a neural network to the moon

January 29, 2021

Using emojis in mathematical notation

Math is hard to understand. Whenever I read technical documents I skip the mathematical equations. When I do read them I have to go over them multiple times to fully finally what the author meant. A...

November 22, 2020

Building a Jack Skellington Mask

This week it’s Halloween Time to dress up as something scary I decided that I wanted to make the mask of Jack Skellington, from “The Nightmare before...

October 28, 2020

Building a Remote Controlled IKEA Table

Inspired by the show Pat and Mat (Buurman en Buurman in the Netherlands) I decided to build a remote controllable IKEA table. For this project I got help from my friend Ilya, with whom we conducted...

October 19, 2020

Visualising lidar and radar in virtual reality

Last week someone pointed out the Astyx dataset to me. So far I only visualised lidar data in my virtual reality tool immersivepoints.com, so I was interested in seeing...

September 27, 2020

Microbe Obliterator (MO) from Wall-e on a mopping robot

My favourite character in the Disney Pixar movie WALL-E is M-O. A while ago I bought a iRobot mopping robot, which always reminded me of Mo. This week I decided to try to pimp up my robot by actually...

August 31, 2020

LEGO Apollo Saturn V Rocket Lamp

I absolutely love everything related to space When decorating our apartment we decided to add a little ‘space corner’ in the hallway for all space related decoration. One thing we bought for this is...

Visualising the PandaSet labels

In May 2020 Scale released their open Autonomous Driving dataset called Pandaset. Of course this is a great opportunity to inspect their data in Virtual Reality with...

Building a Cupcake Robot

Currently, as the corona crisis is causing heavy lockdowns, people have to keep a social distance. This made it difficult to celebrate special events, so as a challenge I decided to try to make a...

Looking back at the first AI Meet VR event

On May 1st 2020 I organised the first AI Meet VR event in Mozilla Hubs. I started organising it two weeks ago to see how a virtual get-together would look and feel like. After experiencing it, I have...

Visualise embeddings in virtual reality

When working with data and neural networks it’s good to know whether similar data is close together. This could be either in the original space of the data or in a deep layer of a neural network. In...

February 16, 2020

Immersive Points: a virtual reality point cloud visualisation tool

A couple of years ago I made a visualization tool for the Google Cardboard that could show you a brain by looking around(../brain-visualisation/index.html). The two big...

January 11, 2020

My new years resolution in super-resolution

A new year is approaching, which means that it’s time for everybody to think about new-years resolutions to improve your life. An ideal moment to take your new-years resolution and turn it into a...

December 15, 2019

A 3D-printed Vehicle Coordinate System

If you work with self-driving cars you probably know about the vehicle coordinate system (also known as ISO 8855). This coordinate system is described extensively...

December 8, 2019

Scale your deep learning on the AWS platform using Horovod

“The more you buy, the more you save”. These are words NVIDIAs CEO Jensen Huang always utters at NVIDIAs GTC conference series. What he refers to is that in machine learning there are often many...

October 17, 2019

Showing kids what neural networks can detect

Last week the company I work for, Autonomous Intelligent Driving, held an open day for children. I showed the kids an object detector to teach kids what Artificial Intelligence can detect.

October 8, 2019

Lessons Learned During a Year at a Self-Driving Car Company

In January I have been a machine learning engineer at Autonomous Intelligent Driving (AID) for exactly a year To summarize for myself what I learned, and to inspire others, I...

I created the InfoQ Alexa skill

A while ago I started exploring the current state of voice interfaces and smart home technology. One particular interesting smart home application is Amazon’s Alexa. It’s a device with a speaker...

January 12, 2019

World’s longest palindrome?

In honor of the 20th of February, 2002, a palindromic date, Peter Norvig designed his worlds longest unique palindromic sentence of 21,012 words. With a new...

Painting by Prime Number

Two weeks ago I stumbled upon the concept of prime portraits. In short, prime portraits are pictures in which each color is assigned a...

Managing our budget with Excel and machine learning

A little over a year ago my girlfriend Lisette and I moved in together. A big part of living together was getting used to managing a budget, and knowing where our money went. Lisette made one of the...

December 14, 2017

Autonomous vehicles will lead others through congested cities

This weekend we got the second place in the Hack the Road Hackathon with our idea to let connected vehicles lead other vehicles through a “green wave”. As there will be a long period in which smart...

September 21, 2017

TRADR SIKS summerschool 2017

A few weeks ago I gave an introductory course to reinforcement learning with the OpenAI Gym environment. As content, I used the writeups I already put on my site several weeks...

September 18, 2017

Detecting bats by recognising their sound with Tensorflow

Last week I discovered that there are bats behind my appartment. I immediately grabbed my “bat detector”: a device that converts the ultrasound signals bats use to echolocate from an inaudible...

Introduction to OpenAI gym part 3: playing Space Invaders with deep reinforcement learning

In part 1 we got to know the openAI Gym environment(../getting-started-openai-gym/index.html), and in part 2 we explored deep...

Introduction to OpenAI gym part 2: building a deep q-network

In part 1 we used a random search algorithm to “solve” the cartpole environment. This time we are going to take things to the next level and implement a deep q-network.The OpenAI gym environment is...

Getting started with OpenAI gym

The OpenAI gym environment is one of the most fun ways to learn more about machine learning. Especially reinforcement learning and neural networks can be applied perfectly to the benchmark and Atari...

The Zalando python client

The Zalando python client

Simple Introduction to Tensorboard Embedding Visualisation

Visualising embeddings is a powerful technique It helps you understand what your algorithm learned, and if this is what you expected it to learn. Embedding visualisation is a standard feature in...

Laser engraving a wine box

This weekend my dad turns 63. This year I created a very personal gift for him: a laser engraved wine box.

What I learned developing the Neural Voting Advice Application

Two weeks ago I put the neural voting advice application online (../neural-voting-advice-application/index.html). In this post, I look back at two aspects: the end-user aspect...

Stemwijzer met kunstmatige intelligentie

Volgende week zijn er verkiezingen in Nederland. Met 28 partijen is dit een lastige keuze. Vaak orienteren mensen zich door een stemwijzer in te vullen. Door de 30 belangrijkste vragen van het moment...

Neural voting advice application

Next week the Netherlands will hold elections to choose who is going to represent the people in the house of representatives. There are 28 political parties participating, although there are 10 ‘big’...

Watching the TensorFlow Dev Summit 2017 – Livestream

Last night Tensorflow held the Dev Summit 2017. Although it was in California, they streamed all talks live through Youtube...

February 15, 2017

Visiting the CLIN 2017 conference – Computational Linguistics in the Netherlands

On 9 and 10 February, the 2017 edition of CLIN (Computational Linguistics in the Netherlands) was held. As I work a lot with neural machine translation, automatic post editing, and translation...

February 13, 2017

Creating photorealistic images with neural networks and a Gameboy Camera

(images/2017/02/mygameboy.jpg) In 1998 Nintendo released the Gameboy Camera. With this camera, it was possible to take images in a resolution of...

February 1, 2017

Explaining Neural Machine Translation to GALA members

Yesterday I presented an introduction to neural networks to GALA members: the Globalization and Localization Association. With the recent breakthrough of Neural Machine Translation (NMT) more and...

January 27, 2017

Old spelling to new Dutch spelling with tensorflow

On February 10 2017 the 27th edition of the Computational Linguistics in the Netherlands conference will be held in Leuven. As part of this conference they organise a “shared task”. This year, this...

January 11, 2017

My top 3 of machine learning advancements in 2016

The year 2017 is starting tomorrow, let’s look back at what happened in machine learning last year. In this blogpost I will post my personal top 3 of developments in Artificial Intelligence this year.

December 31, 2016

Advent of code/testing 2016

This year I participated in the “Advent of Code” challenge. Every day two small programming questions were posted on adventofcode.com that (depending on your skill) could be...

December 25, 2016

Faster writing and testing machine learning applications.

Today I discovered a great thing for people with two computers (development and training). In my case, my normal work-pc is a mediocre Windows computer (company policy) that can’t handle deep...

December 17, 2016

Looking back at my first datathon

In March last year I participated with a team of AI students in the first datathon (hackathon focussed on machine learning) in the Netherlands. The challenge during this hackathon was making the most...

December 15, 2016

Building a Smart IoT Bed

Recently I finished a cool electronics project: internet connected lights under my bed. In three steps I guide you from project to project, each time adding functionality to what we made.

December 9, 2016

Explaining Google’s zero shot translation

(images/2016/11/translationgame2-04.png)Google announced that it can do a zero-shot translation from Korean to Japanese and from Japanese to Korean. They do...

December 1, 2016

Explaining Google’s Neural Machine Translation paper

Google recently published the paper “Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation”: < As I got a lot of...

November 25, 2016

Ineffective sorts: tensorflowsort

Recently sequential neural networks have been gaining popularity. To explore what they were capable of I decided to create the ineffective sorting algorithm (<

November 1, 2016

Calculating how to split your bills

Dutch people are known for splitting their bills. When frequently eating with the same group this could normally lead to an awkward situation, where everybody has to pay everybody a little bit. Most...

October 30, 2016

Connection requests from strangers on LinkedIn: accepting them the right way

Many people talked with me about this dilemma: do you accept connection requests from strangers? Accepting the invite could be a foot in the door in the future, even if you don’t know this person....

February 15, 2016

Brain visualisation

During a project in which I created partitions in the brain there was no simple way to visualise my data. When asking a teacher the best method apparently was: try to write a Matlab script. To help...

November 25, 2014

BNAIC 2014: using human input to improve reinforcement learning

Using human input can be valuable for reinforcement learning. Imagine the difference between having to learn something yourself, and having a mentor hold your hand while showing you how a task is...

November 25, 2014