Watch the talk of the TUM-IAS Wednesday Coffee Talk by Prof. Roberto Giuntini: “Machine Learning meets Quantum Theory”

On 10 January 2024, Prof. Roberto Giuntini (TUM-IAS Philosopher in Residence Fellow / University of Cagliari) presented “Machine Learning meets Quantum Theory”.

Abstract:
Research in the broad area of pattern recognition, machine learning, and quantum computing has inspired new ideas about some important general problems that arise in several disciplines, including information theory (classical and quantum), logic, cognitive science and neuroscience, and philosophy.
One central question that these disciplines often face is the following: How are abstract concepts formed and recognized on the basis of previous (natural or artificial) experiences? Researchers have tackled this problem with diverse methods and tools in both the realms of human intelligence and artificial intelligence. In this seminar, the problem will be addressed within the framework of machine learning and quantum computing. Machine learning can be defined as the art and science of making computers learn from data how to solve problems (or recognize and classify new objects) without being explicitly programmed. Quantum computing describes the processing of information using tools based on the laws of quantum theory. With the explosion of data we are witnessing today, the task of extracting and recognizing valuable information from the data themselves is crucial and yet computationally and resource demanding. On the other hand, quantum computing has shown that there are quantum algorithms that allow a formidable speed-up in solving problems that, classically, would require an exponential running time. The realization of the so-called noisy intermediate-scale quantum (NISQ) computers is now a reality. Therefore, the combination of machine learning and quantum computing seems inevitable. This “marriage” is favored by the ability of quantum theory to effectively handle incomplete information, a crucial aspect in machine learning. The approach that I will present in this seminar (called Quantum Inspired Machine Learning) consists in formally translating the process of (supervised) classification of (classical) machine learning into the language of quantum theory in such a way that the resulting (quantum-like) classification algorithms can be implemented on non-necessarily quantum computers. In particular, I will focus on the problem of binary classification for classical datasets and present the Helstrom Quantum Classifier (HQC), a quantum-like classifier based on the Helstrom protocol used in quantum mechanics to discriminate optimally between two quantum states (mathematically represented by density matrices). HQC acts on density matrices, which, in our model, encode the patterns of a classical dataset. Experimental benchmark results show that the accuracy of HQC is in many cases higher than that of many classical classifiers. The very promising results we have obtained so far seem to clearly indicate that Quantum Inspired Machine Learning could lead to new developments in different fields, from artificial intelligence to medicine.

THE TUM-IAS WEDNESDAY COFFEE TALKS

Every Wednesday after lunch, it's all about a new topic - current research highlights at TUM, insights into the work of our Fellows from all over the world, sometimes even topics not usually found at TUM, such as history or theology.

The talks held online start every Wednesday during TUM lecture time at 1:00 p.m. Everyone is welcome - TUM researchers of all levels, students, visiting scholars, and anyone interested!

Each final Wednesday of the month, a topic related to the United Nations' 17 Sustainable Development Goals will be featured as a part of the Seminar Series of European Universities on Sustainability, a new initiative of the TUM-IAS in partnership with universities across Central, Eastern, and Southeastern Europe.

Would you like to receive regular updates on the TUM-IAS Wednesday Coffee Talk and the online link? Just send a short note to events@ias.tum.de.

An overview of upcoming and past TUM-IAS Wednesday Coffee Talks can be found at the TUM-IAS Wednesday Coffee Talk Overview.