Neural Networks for Chemists

Qingyang Xiao, Kaiyuan Liu, Yuhui Hong, Haixu Tang

Abstract: In recent years, breakthroughs in artificial intelligence (AI) have dramatically transformed many fields. Developments in neural networks primarily drive the advances. These powerful models have demonstrated unprecedented capabilities in learning complex patterns, making predictions, and generating creative content. From the pixels on a smartphone camera to the recommendation systems on a streaming service, neural networks are now ubiquitous and are part of daily interactions. But what exactly are neural networks? They are mathematical models designed to recognize patterns. By learning from data, these networks can make decisions and predictions with remarkable accuracy. However, the true power of neural networks lies in their flexibility and scalability, which allow them to be applied to various tasks, from image recognition to natural language processing and even within biochemistry. This primer is designed as your first step toward understanding neural networks. Whether you are a student, researcher, or industry professional, it will equip you with the knowledge and tools to begin harnessing their power in your work. The authors begin by exploring the basic building blocks of neural networks. Next, they cover fully connected networks, the most straightforward and foundational type of neural networks, as well as more advanced network architectures. The authors also include case studies, discuss representation learning, and provide insights into how these tools accelerate scientific discovery and transform a diverse array of fields, such as healthcare, finance, and beyond.