Quantum Machine Learning with Jessica Pointing

In this episode of The New Quantum Era podcast, hosts Sebastian Hassinger and Kevin Roney interview Jessica Pointing, a PhD student at Oxford studying quantum machine learning.Classical Machine Learning ContextDeep learning has made significant progress, as evidenced by the rapid adoption of ChatGPTNeural networks have a bias towards simple functions, which enables them to generalize well on unseen data despite being highly expressiveThis “simplicity bias” may explain the success of deep learning, defying the traditional bias-variance tradeoffQuantum Neural Networks (QNNs)QNNs are inspired by classical neural networks but have some key differencesThe encoding method used to input classical data into a QNN significantly impacts its inductive biasBasic encoding methods like basis encoding result in a QNN with no useful bias, essentially making it a random learnerAmplitude encoding can introduce a simplicity bias in QNNs, but at the cost of reduced expressivityAmplitude encoding cannot express certain basic functions like XOR/parityThere appears to be a tradeoff between having a good inductive bias and having high expressivity in current QNN frameworksImplications and Future DirectionsCurrent QNN frameworks are unlikely to serve as general purpose learning algorithms that outperform classical neural networksFuture research could explore:Discovering new encoding methods that achieve both good inductive bias and high expressivityIdentifying specific high-value use cases and tailoring QNNs to those problemsDeveloping entirely new QNN architectures and strategiesEvaluating quantum advantage claims requires scrutiny, as current empirical results often rely on comparisons to weak classical baselines or very small-scale experimentsIn summary, this insightful interview with Jessica Pointing highlights the current challenges and open questions in quantum machine learning, providing a framework for critically evaluating progress in the field. While the path to quantum advantage in machine learning remains uncertain, ongoing research continues to expand our understanding of the possibilities and limitations of QNNs.Paper cited in the episode:Do Quantum Neural Networks have Simplicity Bias?