Issue link: https://iconnect007.uberflip.com/i/1518339
14 SMT007 MAGAZINE I APRIL 2024 ition-based optimization process, with train- ing data in the loop to tune DL model param- eters. Training for DL soware occurs "atomi- cally" and with strong coupling across all layers of the DL soware. e increased accuracy of DL soware requires more complex implementations in which the number of layers, their size (number of neurons), and the amount of data used for training increase enormously. Generative AI I tried ChatGPT to see how the bot explains generative AI: "Generative AI refers to a category of artificial intelligence (AI) that focuses on creating new and original content. It uses models and algorithms to generate data, such as text, images, audios, or even videos, that resemble human-created con- tent. Generative AI models are trained on large datasets and can generate creative and coherent outputs based on the patterns and information that have been learned. ey have applications in various fields, including art, language, music, and more." A generative AI model, in a mathematical representation implemented as an algorithm, can create something that didn't previously exist by processing a large amount of visual or textual data and then determining what things are most likely to appear near other things using deep learning or neural networks. Pro- gramming work goes into creating algorithms that can recognize texts or prompts. It creates output by assessing an enormous corpus of data, responding to prompts with something that falls within the realm of probability as determined by that corpus of data. Generative AI tools offer the ability to create essays, images, and music in response to sim- ple prompts. My next column will highlight the founda- tional technologies behind AI, including the large language model (LLM) and foundation model. SMT007 References 1. PwC's Global Artificial Intelligence Study: Exploiting the AI Revolution, pwc.com. Appearances Dr. Jennie Hwang will teach a Professional Devel- opment Course, "Artificial Intelligence – Opportuni- ties, Challenges & Possibilities," on Monday, April 8, at IPC APEX 2024. She will also teach a course titled, "High Reliability Electronics for Harsh Environ- ments" on April 7. Dr. Jennie S. Hwang, an interna- tional businesswoman, interna- tional speaker, and a business and technology advisor, is a pio- neer and long-standing leader in SMT manufacturing since its inception, and in developing and implementing lead-free electronics technology and manufacturing. She has served as chair of Artificial Intelligence- Justified Confidence for DoD Command and Con- trol study, chair of AI Committee of the National Academies, and Review Panels of NSF National AI Institutes. An International Hall of Famer (Women in Technology), she has been inducted into the National Academy of Engineering, named an R&D- Stars-to-Watch, and received the YWCA Achieve- ment Award. She has held senior executive posi- tions with Lockheed Martin Corp., and was CEO of International Electronic Materials Corp. She is cur- rently CEO of H-Technologies Group, providing business, technology, and manufacturing solutions. She has served as chair of the Laboratory Assessment Board, the DoD Army Research Lab- oratory Assessment Board, and the Assessment Board of Army Engineering Centers. She is on the board of Fortune-500 NYSE companies and civic and university boards, Commerce Department's Export Council, National Materials and Manufac- turing Board, NIST Assessment Board, various national panels/committees, and international lead- ership positions. She is the author of 10 books (four as co-author) and 700+ technical/editorial publications. She is a speaker and author on trade, business, and educa- tion issues. Her formal education includes four aca- demic degrees (Ph.D., M.S., M.A., B.S.), as well as Harvard Business School Executive Program and Columbia University Corporate Governance Pro- gram. To read previous columns, click here.