Machine Learning Algorithm

About

The multidisciplinary team at the University of Hertfordshire has developed the machine learning algorithm out of a need to analyse large quantities (100s Terabytes) of imaging and tabular astrophysics data. The data had to be mined and analysed to make new discoveries and the resulting data analysis tools using statistics, machine learning and modelling has a wide variety of applications in other areas that involve big data. The main focus of the technology is in unsupervised machine learning techniques and the application of biologically-inspired machine learning algorithms for the analysis of real world data. Unsupervised learning has the advantage that it does not rely on training data but rather finds latent structure and trends in large input data sets (such as databases and images). The algorithm used has been proven in the automatic classification of galaxies in Hubble space telescope imaging and the university is currently working to prove the algorithm in myocardial perfusion scanning to improve early diagnosis of heart disease. In this regard the algorithm is very flexible and the techniques used map across a wide range of disparate fields. The algorithm has potential in a number of areas including: Identifying consumer patterns (e.g. supermarkets, online retail) Predictive analysis /automatic suggestion (e.g. online retail) Autonomous classification (e.g. medicine, defence, security) Autonomous navigation (e.g. driverless vehicles) The machine learning algorithm  and the computer science team that has developed this can offer: Bespoke solutions for complex data analysis tasks Access to expertise in cutting-edge data analysis and machine learning techniques Discovery in big data sets without the need to “teach” the system The ability to run the algorithm on an ordinary PC or laptop – unlike other algorithms that require vast computing power. See the video here: https://www.youtube.com/watch?v=DzbV_4-HuIk The University is looking for technical cooperation partners, investors or partners would like to license the technology.   If you would like to speak with Enterprise Europe Network about the University before contacting them directly please contact: Nicky Whiting – Innovation Advisor [email protected] +44(0)7921353734