EvoTorch is the first of its kind open-source platform for machine learning researchers and engineers that uses evolutionary algorithms to drive optimization and catalyse industry growth. Combined with machine learning expertise, it can solve complex operational challenges in a fraction of the time, at lower costs and greater scale.
With machine learning playing an increasingly vital role in many industrial verticals, evolutionary algorithms (EA) are an attractive solution to cascading challenges that accompany the increased complexity and size of automated processes. With EA, a wider variety of problems, from learning robot controllers to optimizing schedules or product designs, can be tackled with greater efficiency. However, a software tool-set that makes it simple to experiment with EAs at any scale without worrying about the underlying details has been missing.
Swiss AI company, NNAISENSE, has launched EvoTorch, an open-source evolutionary algorithm library to provide researchers, developers and industrial manufacturers with powerful EAs that can be scaled across CPUs or GPUs with no extra effort, speeding up optimization and minimizing costs. EvoTorch is built on the back of the open-source PyTorch machine learning library and Ray packages used for Python and AI applications.
"The goal of EvoTorch is to create an open-source ML community and facilitate the adoption of EAs within the field of automation by providing researchers and engineers with the tools to scale up their designs easily and quickly," said Rupesh Srivastava, Director of Software Infrastructure at NNAISENSE. The additional strength of this platform lies in the expert support we offer to commercial users, assisting them with effective customization, implementation and oversight. We will continuously expand our features to help users based on the data we acquire from ongoing projects, leading to a wider range of field-tested building blocks to spur on industry growth."
Condensing 180 years drive simulations into 24 hours
"In a pioneering project with Audi - where we worked on their autonomous parking system - we highlighted how much time could be saved by parallelizing evolutionary algorithms to achieve operational goals for industry. Using this technique, we condensed 180 years worth of simulated driving time into 24 hours," said Jan Koutnik, Co-founder & Director of Intelligent Automation at NNAISENSE.
Given its ever-expanding range of EAs and its intuitive interface, EvoTorch can also greatly simplify the job of academics and university students developing new algorithms, helping catalyze R&D in this field.
NNAISENSE is a leader in AI engineering for industrial applications. The company's founders are all veterans of the renowned Swiss AI lab IDSIA, co-directed by Professor Jürgen Schmidhuber (Chief Scientist at NNAISENSE). Among NNAISENSE's notable contributions is the creation of the first RL-based autonomous parking system for Audi and training controllers for the Festo pneumatic robot 'soft' hand. NNAISENSE's client and Investor base include Samsung, Audi, Trumpf GmbH + Co. KG, EOS GmbH and Schott AG, among others.
(Press release)
Please login or sign up to comment.
Commenting guidelines