Our researchers use AI to improve AI
In the age of big data, being able to find the value in large amounts of information can make or break a business. Our IBM Research team specialises in developing AI solutions that intelligently find the value in real-world data, and exploit this to solve important industrial challenges.
Bayesian optimisation is a way to search through this data intelligently. It's used to solve a variety of problems in fields as varied as robotics, animation, planning, and experimental particle physics.
Its power lies in accurately solving complex problems by dramatically cutting down the number of costly experiments or simulations. It does this by intelligently predicting which experiments are likely to yield positive outcomes, and updating these predictions when more information is available.
You could even say that our algorithm understands when it can trust itself, and when it needs to seek more information. Think of it as "AI for design."
Our researchers have created Bayesian Optimization Accelerator (BOA) that can rapidly find solutions for tough challenges: designing components for engineering problems, creating powerful neural networks, and discovering molecular compositions that will lead to breakthrough drugs.
Come and see how easily you can integrate this powerful technique into your own workflow from a very simple web user interface. It quickly sets up, monitors, and explains the whole process. You don't need to become an expert in a complex mathematical discipline to use state-of-the-art intelligent optimisation.