演講主題： Insights into Green AI: Methodologies and Applications
演講時間：2026年4月13日（星期一）上午10:30~11:30
演講地點：大仁樓三樓301教室
演講摘要： Rapid AI advances in the last decade have been largely driven by the widespread adoption of deep learning (DL). Yet, the growing carbon footprint of large DL networks has been a concern for sustainability. Furthermore, the DL decision mechanism is obscure. As an alternative, I have conducted research on green AI and green learning (GL). GL does not have neurons, neural networks, or backpropagation. Instead, it uses statistical tools to determine the parameters of an AI model in a feedforward manner. GL contains three modules in cascade: representation learning, feature learning, and decision learning. I will explain the intuition behind each module and the computational algorithms. GL offers energy-efficient solutions in data centers and mobile and edge devices. GL has been successfully applied to various applications. I will use several examples to demonstrate the effectiveness and efficiency of GL.
資訊學院將於 4月13日（星期一）上午10點30分，邀請 中央研究院院士、南加州大學 郭宗杰教授 蒞臨本校，進行專題演講。歡迎有興趣的師生踴躍參加。