AI2FUTURE 2024 – 2 days, 50+ moving & inspiring discussion and presentations

17th & 18th of October 2024, Kraš Auditorium, Zagreb, Croatia
https://i0.wp.com/ai2future.com/wp-content/uploads/2023/09/Ema-Puljak.jpg?fit=320%2C303&ssl=1
UAB (Universitat Autonoma de Barcelona)

Ema Puljak

Doctoral Researcher in Quantum Machine Learning

Ema Puljak is a doctoral student at the University Autonoma Barcelona specializing in the interdisciplinary field of Quantum Computing and Machine Learning. She was conducting her cutting-edge research at CERN, one of the world’s most prestigious research centers, in collaboration with the Barcelona Supercomputing Center. Ema’s academic journey began at the Faculty of Electrical Engineering and Computing (FER) in Zagreb, where she earned her degree in computer science. Her path to advanced research was paved by a significant internship at CERN, where she worked on developing artificial intelligence algorithms aimed at enhancing particle discovery processes. This experience fueled her interest in the potential of quantum computing combined with machine learning to solve complex, real-world problems, leading her to her current research focus.


Ema’s

Idea

Bridging the Gap: How Tensor Networks Connect Classical and Quantum Machine Learning

This talk addresses the intriguing question of whether Machine Learning algorithms can benefit from the advancements in Quantum Computing. It begins by introducing Tensor Networks, Quantum-Inspired algorithms that serve as a crucial link between classical and quantum world. These networks are explored for their ability to enhance the performance of classical Machine Learning by optimizing data processing and reducing computational complexity.
The talk then transitions to examine the connection between Tensor Networks and Quantum Machine Learning algorithms, as Tensor Networks can be seen as a classical approximation of quantum states. This connection opens the door to understanding how quantum algorithms might outperform their classical counterparts, a phenomenon known as quantum advantage. However, proving a quantum advantage in ML is not straightforward. Researchers must consider various factors, including the types of problems quantum algorithms are best suited for, the current limitations of quantum hardware, and how to benchmark these algorithms against classical ones.
Designed to be informative and accessible, this talk will be valuable whether you are new to the field or looking to deepen your knowledge of the intersection between Quantum Computing and Machine Learning.