Optimizing complex processes using AI
We develop algorithms and software solutions for optimizing complex processes such as road traffic and cancer treatment. Despite the fact that processes are from different domains, they (unexpectedly) share many interesting properties and can be tackled using similar techniques.
In the case of road traffic optimization, our tools may help in, e.g., building better traffic signal control systems and reducing travel times.
In the case of cancer treatment, our methods may help doctors and medical research institutions find better radiotherapy strategies.
Our methods are mainly based on AI and multiagent simulations based on cellular automata, hence the name TensorCell (tensors are just mathematical objects which are extensively used in machine learning; cells are building blocks of cellular automata).
Simply, we use cellular automata which can be highly parallelized to simulate complex processes, we train machine learning models to approximate the outcomes of the simulations in order to accelerate computations even faster, and finally, we use evolutionary algorithms and reinforcement learning to optimize the complex processes. You can read more in the section Research.
You can also follow us on social media: