GET THE APP

International Health Informatics Journals | Open Access Journals
Journal of Health & Medical Informatics

Journal of Health & Medical Informatics

ISSN: 2157-7420

Open Access

International Health Informatics Journals

Machine learning (ML) is that the fastest-growing field in computing and health informatics is among the best challenges. The goal of ML is to develop algorithms that may learn and improve over time and may be used for predictions. Most ML researchers consider automatic machine learning (aML), where great advances are made, for instance, in speech recognition, recommender systems, or autonomous vehicles. Automatic approaches greatly enjoy big data with many training sets. However, within the health domain, sometimes we are confronted with a little number of knowledge sets or rare events, where aML-approaches suffer of insufficient training samples. Here interactive machine learning (iML) could also be of help, having its roots in reinforcement learning, preference learning, and active learning. The term iML isn't yet well used, so we define it as ‘‘algorithms which will interact with agents and may optimize their learning behavior through these interactions, where the agents also can be human.’’ This ‘‘human-in-the-loop’’ is often beneficial in solving computationally hard problems, e.g., subspace clustering, folding, or k-anonymization of health data, where human expertise can help to scale back an exponential search space through heuristic selection of samples. Therefore, what would rather be an NP-hard problem, reduces greatly in complexity through the input and therefore the assistance of a person's agent involved within the learning phase.

High Impact List of Articles
Conference Proceedings

Relevant Topics in Medical Sciences

Google Scholar citation report
Citations: 2700

Journal of Health & Medical Informatics received 2700 citations as per Google Scholar report

Journal of Health & Medical Informatics peer review process verified at publons

Indexed In

 
arrow_upward arrow_upward