Gawehn E, Hiss JA, and Schneider G. Deep Learning in Drug Discovery. Molecular Informatics 2016; 35(1): 3-14.

Click here to view the paper

Currently, machine learning methods drive the success of artificial intelligence in academia and industry. Among machine learning methods, Deep Learning has emerged as a game-changer in many fields and has already impacted a wide range of scientific areas.1 Deep Learning is founded on novel algorithms and architectures together with the recent availability of very fast computers and massive data sets. In its core, Deep Learning discovers multiple levels of distributed representations of the input, with higher levels representing more abstract concepts. These representations considerably improved data analysis in many research areas. In particular, deep neural networks (DNNs) substantially increased the performance in computer vision, speech recognition, among many other fields. Surprisingly, models developed in a number of fields have reached human performance or above. Nevertheless, the risk of overfitting remains and care has to be taken to not overestimate the generality models can achieve.

The full list of the top 100 articles on artificial intelligence and artificial intelligence in medicine are published here:

Intelligence- Based Medicine
Artificial Intelligence and Human Cognition in Clinical Medicine and Healthcare.
Anthony Chang, MD, MBA, MPH, MS