The future of artificial intelligence (AI) is looking brighter than ever. In a recent breakthrough, researchers have developed a new AI system called GPT-Chem that can accurately predict the properties of molecules with up to 99% accuracy. This is a major step forward in the field of AI-driven chemistry, and paves the way for a range of applications in drug discovery, materials science, and more.

At its core, GPT-Chem is a machine learning algorithm based on a type of AI known as “transformer” networks. These networks are trained on large datasets and can learn to make accurate predictions without being explicitly programmed. In the case of GPT-Chem, the team trained the network on millions of molecules and their associated properties. By doing so, the AI was able to learn to accurately predict the properties of new molecules that it had never seen before.

This breakthrough has the potential to revolutionize the field of AI-driven chemistry. By allowing researchers to quickly and accurately predict the properties of molecules, GPT-Chem could make drug discovery more efficient and cost-effective, and could also be used to develop new materials with improved properties. It could even be used to predict the properties of molecules that don’

Read Full Article Here

source: Phys.org