MCL Director, Professor Kuo, gave a keynote speech at 5the G/B5G Mobile Broadband Communication Forum in KaoHsiung, Taiwan, on December 14, 2019. The title of his keynote was “On Efficient and Explainable AI/ML Techniques for 5G/B5G Broadband Communication Systems”. Here is the abstract of his speech.
“There have been many successful artificial intelligence and machine learning (AI/ML) stories in the last decade due to the resurgence of neural-network-based deep learning. We may ask whether the amazing success is primarily attributed to “deep learning” or “big data”. If it is attributed to deep learning, we need to understand these tools fully and open the black-box for further advancement. If it is attributed to big data, we need to find a way to position ourselves since data collection and labeling are expensive. With respect to the first question, I argue that AI is not necessarily dependent upon deep learning. We are working on an alternative approach, called Successive Subspace Learning (SSL), to solve the big data problem at USC. SSL is mathematically transparent and expandable depending on the training data sizes and classes. It has great potential. With respect to the second question, my view is that big data is helpful but not sufficient by itself. It is essential to integrate the “rule-based” and the “data-driven” approaches for generalizability and robustness. It leads to the conclusion that AI/ML is not about competing with humans in terms of intelligence but an advanced form of “automation”, which leverages both data and domain knowledge to achieve domain-specific tasks more effectively. Finally, I will give a couple of examples on how to apply AI/ML techniques to 5G/B5G broadband communication systems.”