My Projects

• Quantum Convolutional Neural Network Architecture for multi-class image classification
  IEEE International Joint Conference on Neural Networks (IJCNN), 2023
  Samarth Kashyap, Shayan Srinivasa Garani
  

  There have been many attempts at translating classical machine learning algorithms to quantum circuits. Our architecture utilizes generalized 3-qubit parametrized unitary gates to perform image classification. However, simply copying the architecture to use quantum circuits does not result in similar transformations, so we introduce an encoding scheme that allows us to preserve the quasilocal transformations of a convolutional neural network. The results are promising, with 80% accuracy on the 10-class MNIST dataset, with further improvements from decreasing the number of classes, leading up to a 99% accuracy on a 2-class dataset. However, it is important to keep in mind that image classification is not necessarily a task that benefits from a quantum algorithm due to encoding constraints. MNIST classification is simply a benchmark to show the feasibility of our architecture and compare it to existing algorithms, quantum and classical. There is further ongoing research to apply this architecture to problems that are more suited to quantum computing.

  Find the code for this project here.

• Advances in Machine Learning: Where Can Quantum Techniques Help?
  arXiv preprint, 2025
  Samarth Kashyap, Rohit K Ramakrishnan, Kumari Jyoti, Apoorva D Patel
  

  This paper reviews the current state of quantum machine learning, focusing on analysis of how and where quantum techniques can be applied to machine learning problems. We introduce the theoretical foundations of QML, including quantum data encoding, quantum learning theory and optimization techniques, while categorizing QML approaches based on data type and computational architecture. It is well-established that quantum computational advantages are problem-dependent, and so potentially useful directions for QML need to be systematically identified. This comprehensive analysis underscores that while QML has significant potential for specific applications such as quantum chemistry and sensing, its broader utility in real-world scenarios remains contingent on overcoming technological and methodological hurdles.