In this Ekkono SWP (Short White Paper) we introduce Incremental Learning – how you continuously can learn from streaming sensor data, train individually models per device, start with little or no data, etc.
A traditional Machine Learning approach relies on the fact that data has been collected and is readily available in some kind of data storage. Incremental Learning does not require that a large amount of data has been collected before the model is trained. Instead learning starts with a very simple model typically predicting the average value seen so far. When new data examples arrive, the model is trained to be able to predict the new example. Learn more in our SWP about Incremental Learning.
Click the image to download the SWP document (pdf).
Ekkono’s SWP are documented results of our #openfika webinars.
The webinars are also recorded and available to watch in our YouTube channel or below: