It’s not magic, it’s data!
Countless companies are either working on machine learning projects or are dreaming of using the technology as quickly as possible. However over time, many of these ambitious projects don’t deliver the desired outcome. This is often due to the poor quality of the available data that are fed into the algorithms. “Garbage in, garbage out” is an iron law in the field of machine learning. That’s why data scientists are of crucial importance in any machine learning project. They analyze and clean the data, transform it into the desired format with the required quality
It’s training cats and dogs
Image recognition is one of the biggest success stories of machine learning technology and can be found everywhere in our lives, used daily by thousands of companies and millions of consumers. Image recognition is driven by deep learning and more exactly by Convolutional Neural Networks (CNN), a specific neural network architecture. CNNs have been successfully applied to identify faces, objects, road signs, to implement filters on your smartphone. It gives vision to robotics applications and fuels the self-driving car. CNN applications are not limited to these cases. They also allow computers to distinguish cats from dogs. Let’s dive right in and have a look under the CNN hood!
Serving GPflow models
Deploying models as webservices has become straightforward using TensorFlow: exporting the graph as SavedModel allows easy deployment with Tensorflow Serve or the Cloud ML engine. But how can you obtain a SavedModel when using the GPflow library for Gaussian Processes?
Recommendations systems are not new. In 2006, Netflix started a one million dollar competition to improve their recommendation algorithms. In 2019, 75% of their viewed content is attributed to personalized recommendations.
Learn about how this technology allows you to personalize the interactions between your customers via dedicated newsletters, promotions or your website.
ML2Grow’s secret recipe for customer churn prediction
Customers churn when they stop purchasing your goods or services. While usually no expense is spared to find and attract new customers, the same seldom applies to identifying customers which are ready to join your competitor. But how exactly can you focus your efforts to the right customer, find out in this article!
It’s a match! ML2Grow welcomes three new colleagues
We were able to welcome no less than three new colleagues in October! Anton arrived as software engineer after he did his master’s thesis with Joeri. Julie and Mike are completely new and come to complete our team as data scientists.
Introducing μDatastore, an ODM for Google Cloud Datastore
ML2Grow releases an open source Object-Document Mapper framework for use with the Google Cloud Datastore.
ML2Grow is deploying machine learning at the Port of Antwerp to enable 8-hour lookahead capacity planning
There is a worldwide growth of shipping traffic challenges, planning routines and systems in large trading hubs, such as the Port of Antwerp. CVBA Brabo -a company with a long history of piloting and (un)mooring ships in the ports of Antwerp, Zeebrugge and the canal to Brussels-, is working together with ML2Grow to cope with this demanding evolution. In particular, advanced machine learning techniques are being used to plan further ahead and with higher precision.
Towards an accurate yield prediction in tomato greenhouses
ML2Grow is installing sensors and gathering data at the Tomato Masters facility
Deploying a private package repository on Google App Engine
ML2Grow developers release an open source project for setting up a private package repository on Google cloud