Machine learning applications do not need a huge amount of data for learning

A group of researchers from the University of British Columbia has discovered that some machine learning applications can learn from less data. They published their paper in the journal “nature machine intelligence”.

The team interprets the testing they performed with machine learning applications created to predict certain types of molecular structures. In this new effort, researchers found that machine learning applications such as spotting people in photographs do not need huge amounts of data to be useful.

The discovery paves the way towards the scope to develop more machine learning applications in major sectors like health care and finance.

Related posts

Leave a Comment