An Advanced Evolutionary library or algorithm has been a dream of scientists and AI/ML enthusiasts since the concept was introduced. This vision has come true thanks to the scientists at NNAISENSE, a Switzerland-based AI Enterprise. They created an open-source platform called EvoTorch. When operated in combination with Machine Learning, it can solve complex operational problems in a fraction of time, with lower costs, and at a larger scale. Evolutionary algorithms act as a step toward solving cascading problems that occur when the problem’s size and complexity increase. Evolutionary algorithms make the situations easier to handle the complexity without adding to the cost, they are also much easier to connect through GPUs and CPUs parallelly to ease up the calculation time and the complexity associated with it, that the only limit to your computational power becomes your budget. The evolutionary algorithms are built in the open framework EvoTorch.
EvoTorch is a platform that is built upon PyTorch and will be used to optimize the models that have been constructed on the PyTorch platform, the main advantage being that EvoTorch is made in such a way that it scales up to thousands of CPU and hundreds of GPU which can help in decreasing the computational time by a lot and for a lot more considerable dataset than the previous frameworks allowed. The purpose of EAs is to create an open source community that will provide tools to the researchers and engineers to scale up their models and designs easily and quickly. In project collaboration with Audi on their autonomous parking system, It was highlighted that a huge amount of time could be saved by parallelizing evolutionary algorithms to achieve the results as they were able to compute a dataset having 180 years of data in just 24 hours.
These algorithms are based upon the principle of survival of the fittest, where they choose the best solutions that fit the problem. After every cycle, the weaker solutions are eliminated, and better fitting solutions go through another cycle, which helps provide the best solution for the problem. EvoTorch is built upon the easy-to-use PyTorch interface and helps in integrating EA with the famous and already known ML algorithms, which in the end will help in incorporating flows much easier and faster, which will in the future help the young researchers and university students in their academics, and hopes to catalyze the R&D in the field.
A Machine Learning enthusiast who loves to research and get to know new and latest technologies like AlphaFold, DeepMind AlphaZero etc. that are the best AI in their respective fields and I am very excited what the future of AI and how we will implement it in our daily life