Kunpeng Zhang

As long ago as 2010, Eric Schmidt, the executive chairman of Alphabet, observed that every two days we generate as much information as was created in the entire history of civilization until 2003. The problem is only that much of this information is unstructured by not being organized in a pre-defined manner. This lack of structure complicates extracting useful insights from these massively increasing data sources. Students should have some familiarity with the Python/R programming. Please bring a laptop to class. You also need a Google account to practice using Colab. Learning objectives and course content In this class, we will explore different statistical approaches that have proven useful in making sense out of unstructured data. The course is centered around business applications that involve the analyses of text, social networks, images as well as well as their relationships with meta-data. For most of the analyses, we will use Python/R and dedicate some of the class sessions to hands-on time. Students are invited to bring their unstructured data sets but doing so is not required.

In recent years, AI technology, specifically LLMs like GPT-3 and GPT-4, have shown an impressive capacity to generate human-like text, enabling new applications in creative writing, chatbots, language translation, and more. However, understanding and effectively leveraging these models can be a complex task due to their sophisticated architecture and the vast amounts of data they require. This course aims to equip learners with the knowledge and skills to navigate these challenges, demystify the underlying principles of LLMs, and explore practical applications. It is designed for AI practition-ers, researchers, and enthusiasts who aspire to harness the power of generative AI in their work or research. Participants will gain a basic understanding of AI and foundational concepts of large language mod-els. They will learn the key components and architecture of models like ChatGPT, and how they are trained to generate human-like text. Students will gain a deep understanding of how to implement these generative AI models for a variety of tasks, such as text generation, text completion, and more complex applications like question an-swering, translation, and summarization. Students will learn how to use these existing pre-trained models via prompt engineering or fine-tune models for various NLP tasks in different domains like finance, marketing, healthcare, and education. Students will have hands-on experience in these areas. As AI grows increasingly powerful, it’s important to understand the ethical implications. Students can expect to learn about the ethical, societal, and legal issues surrounding the use of Large Language Models, including biases in AI, privacy concerns, and the potential misuse of these models.