Prof. Sashikumaar Ganesan, Thivin Anandh, Divij Ghose, Himanshu Jain
FastVPINNs is an hp-Variational Physics Informed Neural Network framework that significantly reduces computational overhead and improves scalability. Using optimized tensor operations for calculating the variational loss function, FastVPINNs can achieve a 100-fold reduction in the median training time per epoch compared to traditional hp-VPINNs. With proper choice of hyperparameters, FastVPINNs surpass conventional PINNs in both speed and accuracy, especially in problems with high-frequency solutions. Demonstrated effectiveness in solving inverse problems on complex domains underscores FastVPINNs’ potential for widespread application in scientific and engineering challenges, opening new avenues for practical implementations in scientific machine learning.
FastVPINNs is now available as a PyPI package.You can import it from CLI using the following command
pip install fastvpinns AI for Defence
Prof. Sashikumaar Ganesan, Lokesh, Protyush and the team
AI for Defence involves developing state-of-the-art machine learning models to integrate AI into combat aircraft. Some of its core components include the following:
MULTI SENSOR DATA FUSION | RETRIEVAL AUGMENTED GENERATION | EXPLAINABLE AI | LLM POWERED AI TOOLS