Humans have a natural profound understanding about the physical world we are born in. We know how objects move, and where they are located in relation to us. For example, if we know that the cloud is above the house, it's obvious that the house is below the cloud. This kind of common sense knowledge is learned implicitly and is difficult to capture by machine systems.
Generating an endless feed of fake but realistic training data to perfect our invoice recognition model.
At IxorThink, we recently finished the second phase of development of the epileptic seizure detection system on EEG brainwaves. This detection system was developed in collaboration with Professor Dr. Robrecht Raedt, 4BrainLab, Ghent University.
The use of modern cloud services offers interesting opportunities in terms of cost, administrative ease and scalability. You only pay for the number of seconds your code is actually running, which makes it in general much cheaper than hosting your own server 24/7.
About two years ago, we started developing a machine learning model for named entity recognition (NER) on invoices. With more data available now, we believe it is possible to make a big leap in performance by changing our AI model architecture. To achieve state-of-the-art performance, it is necessary to combine information from content and layout. To tackle this, we use an artificial neural network trained on our invoice dataset.
Approximately 50 million people worldwide have epilepsy, making it one of the most common neurological diseases globally. In one of our recent projects for the Ghent University Hospital, we had to tackle the problem of detecting epileptic seizures in EEG signal recordings of rats and mice. In this project, we go one step further than existing epilepsy detection projects; we detect the exact start and end time of an epileptic seizure.
To improve the end-users trust, Ixor adopts the information provided by intermediate results (feature maps) of the model to give more context to the prediction. The key idea is that similar inputs generate similar feature maps. The similarity of these can be calculated and when stored we have a database of how similar inputs are to each other.
At IxorThink a simple framework for using active learning in object detection has been proposed to significantly save time and resources on the labeling efforts to train an object detection model. In addition to that, the proposed work proved to be effective in improving the model’s performance after the production stage.
One of the most common problems that can be faced when using machine learning is having an imbalanced dataset. Multiple approaches have been used to address this problem, whether on the algorithm’s level or data level. This was particularly a problem in out datasets of medical scans.
Following the rise of deep learning, AI is making its way into the medical sector. A recent study showed that AI could detect breast cancer based on screening mammograms with comparable accuracy as expert radiologists. The study was able to achieve these excellent results not only because of the model development by Google Deepmind AI, but also because of a dataset that consisted out of almost 29,000 mammograms.