Machine Learning

QED has been involved with the development of artificial intelligence solutions for many industrial clients requiring computerized classification and prediction. In contrast to other data science shops, our experience combines both modern machine learning approaches — such as support vector machines, random forests, neural networks, and naive Bayes — with more classical modeling techniques such as point estimation, time series analysis, markov decision processes, and statistical signal processing.

Our team’s high fluency in both computer science and rigorous statistical theory provides us with the agility to easily transition and sample from both cultures of statistical modeling that were perceived by Breiman. Many of our applications are related to computer vision, which is described in fuller detail in a separate section.