jdsoft meets tothepoint and onthespot

JdSoft creates advanced Fireplug application for emergency services with ToThePoint IT consultancy collaboration

The extra resources that ToThePoint and its subcompany OnTheSpot provided ensured the necessary progress to meet the deadline that JdSoft laid in place for itself. A basic functioning Fireplug application will be available to showcase at the INFOPOL exposition in time, as projected.

Kevin Smeyers, machine learning expert and technical architect at ToThePoint is featured on the applied machine learning days website

Our Machine Learning expert Kevin Smeyers is scheduled to talk at #AMLD2019, Switzerland

About AMLD2019 The “Applied Machine Learning Days” is a yearly recurring event that lasts “four days with talks, tutorials & workshops about Machine Learning and Artifical Intelligence with top speakers from around the world” (-AMLD). Tickets for AMLD2019 can be found on their website. Why we applied to talk We’ve discovered a multitude of learnings …

Our Machine Learning expert Kevin Smeyers is scheduled to talk at #AMLD2019, Switzerland Read More »

ElasticSearch percolator dynamic

Matching documents with queries using the Elasticsearch Percolator query Introduction

Recently, on one of my projects, a real estate website, a new story popped-up telling us that we should use the search preferences (price, type of real estate, location), that registered users can save, to send notifications to these users, when a new house or appartement is published on the website. Not immediately having a …

Matching documents with queries using the Elasticsearch Percolator query Introduction Read More »

Accessing Kafka on Google Kubernetes Engine from the outside world

Accessing Kafka on Google Kubernetes Engine from the outside world

Running and operating a Kafka cluster on Kubernetes can be a tricky part. There are already many tutorials, blogpost, Helm Charts, Operators, … that will give you detailed information on installing a working Kafka cluster on Kubernetes with StatefulSets, Headless services and other Kubernetes features. But after going through all those and when finally getting …

Accessing Kafka on Google Kubernetes Engine from the outside world Read More »

Arcadekast tornooi data verzamelen voor machine learning

#5 Case study Machine Learning: ToTheArcade: the architecture

Okay, went on a small vacation in between, so this blogpost took a little longer to write since me and the kids were busy mastering our best splash in the hotel swimming pool.   Where was I?  Right, preprocessing: check, features: check, our models: check, so now it’s time to put these bad boys into …

#5 Case study Machine Learning: ToTheArcade: the architecture Read More »

Machine learning

#4 Case Study Machine Learning: ToTheArcade: diving into the models

Since the last blogpost, I left my feature engineering journey behind and can now finally can start looking at some models. No Free Lunch Theorem During my Machine Learning journey, I looked at 3 models  (‘she’s a model and she’s looking good…’ – Kraftwerk). Why we didn’t stick with only one? Well, in Machine Learning …

#4 Case Study Machine Learning: ToTheArcade: diving into the models Read More »

code on screen

#3 Case Study Machine Learning: ToTheArcade: final feature engineering part

Last blogpost we discussed the problem and we started working a bit on describing our task environment. To summarize: We structured our data, got rid of the noise, and already identified some difficulties we’ll have to cope with.  More precisely, the task environment for our classification agent is quite complex, because of the many unknown …

#3 Case Study Machine Learning: ToTheArcade: final feature engineering part Read More »