Milan is the technical mastermind of Mentio. He built the integration to Xero, databases, algorithms and interface. While a back-end guru through his technological DNA, he...more also managed to build the front-end of the app too. Luckily, Milan now has other developers to guide as the engine and the interface evolve.
Milan is too humble to boast about his accomplishments. But those around him would state that he is a workhorse producing extremely solid code.
Milan is our CTO, leading the tech team and development. He has a PhD in CompSci and specialties in machines learning and natural language processing, as well as lots of experience designing BI tools....more This gives him all the skills required for developing the Mentio algorithms which will become smarter with more cases and usage.Monique Morden
Milan provides technical oversight and guidance on a variety of software projects for Optimus. This includes technical and architectural oversight to a number of small start-up...more SaaS companies and independent technical, architectural and software development process reviews for potential investors interested in investing in small start-up companies. Other projects include web-based and mobile applications grounded in business intelligence.
2006 - 2014 (over 7 years)
Milan was involved in next generation ad-hoc query tools that let people create reports in plain English. This involved expert systems for automatic data warehouse and OLAP...more cube creation, which enabled information extraction from resumes.
Milan created automatic information retrieval from free text for the aerospace industry fed into a business intelligence solution. For the healthcare industry, Milan was involved...more in the creation of automatic third party liability detection and fraud detection.
Researcher, Developer, Author · Developed algorithms (mostly machine-learning based) and published a couple of papers on Illumination Estimation (aka… · More white balancing for cameras) as part of my PhD.
Developer, Analyst, Researcher · Automatic white balancing works quite well on average, but seriously fails some of the time leading to completely… · More unacceptable images. Since the main source of error in automatic white balancing arises from misidentifying the overall scene illuminant, a new illumination estimation algorithm is presented that minimizes the high percentile error of its estimates. The algorithm combines illumination estimates from standard existing algorithms and chromaticity gamut characteristics of the image as features in a feature space. The probability estimation is based on Loftsgaarden-Quesenberry multivariate density function estimation over the feature vectors derived from a set of synthetic training images. Once the probability distribution estimate for a given chromaticity channel is known, the smallest interval that is likely to contain the right answer with a desired probability is chosen. Testing on a dataset of real images shows that the error at the 90th and 98th percentile ranges can be reduced by roughly half, with minimal impact on the mean error.
What I Do
Awe-Inspiring Algorithm Architect - I love leveraging the power of computing to easily solve very complex problems. There is beauty in simplicity but the complexity in generating it for the user. I get to use my passion to help small business owners succeed by giving them simple business tasks.
Immigrating from Slovakia. Post secondary education in Canada was a way to a better life.
My university degrees have given me a strong foundation: MSc in Artificial Intelligence & Natural Language Processing and PhD in Computer Science.
In late 1990's, I was part of a team of three that tried to do (somewhat successfully) what Microsoft Power BI natural language query is doing now - question answering service that analyzes free form English questions and translates them to SQL (or other) queries and reports.
Developed sophisticated text processing algorithms using a combination of machine learning and linguistics-based natural language processing techniques to analyze free form English text in the aviation and health care domains. Some algorithms were patented.
Developed a novel ad-hoc database query tool that guides users in the creation of (non-free form) English queries. The tool instantaneously answers the questions with fully formatted interactive graphic dashboards.
Milan is our CTO, leading the tech team and development. He has a PhD in CompSci and specialties in machines learning and natural language processing, as well as lots of experience designing BI tools. This gives him all the skills required for developing the Mentio algorithms which will become smarter with more cases and usage.