Add to Favourites
To login click here
Researchers at the University of Bristol have developed a new method for augmenting neural network training with artificially generated data that mimics the behavior of real-world systems. This data can be used to train AI/ML-based perception models, which can help to improve the accuracy of predictions on unseen data and scenarios. Simulation is one of the strongest tools in collecting synthetic data and can generate large quantities of it to cover a wide range of conditions.