Course

Syllabus

Classical ML with Pseudo inverse, Kernel Methods and Neural Networks, Quantum Linear Algebra, Quantum Kernel Methods – Quantum Neural Networks, QSVM Algorithm, QKmean Algorithm, QPCA Algorithm, QPerceptron Algorithm. Quantum Transformer.

Course Objectives

1. Understand the classical machine learning, pseudo-inverse methods and kernel methods.
2. Understand the Quantum-enhanced kernel methods and types of Kernels.
3. To explore quantum machine learning algorithms such as QSVM, QK-Means, QPCA, and QPerceptron.
4. Understand the quantum neural networks and quantum transformer architectures.

CourseOutcomes

• CO1: Explain classical machine learning techniques including pseudo-inverse methods, kernel methods, and neural networks.
• CO2: Apply quantum linear algebra concepts and quantum kernel methods in machine learning tasks.
• CO3: Analyze and implement quantum machine learning algorithms such as QSVM, QK-Means, QPCA, and QPerceptron.
• CO4: Evaluate advanced quantum models including quantum neural networks and quantum transformer architectures.

Evaluation Pattern: 70:30

TEXTBOOKS

1. Maria Schuld and Francesco Petruccione, Machine Learning with Quantum Computers, 2nd Edition, Springer, 2021.
2. Peter Wittek, Quantum Machine Learning: What Quantum Computing Means to Data Mining, Academic Press.

REFERENCES

1. Seth Lloyd, Masoud Mohseni, and Patrick Rebentrost, Research papers on Quantum Algorithms for Machine Learning (QSVM, QPCA).
2. Vojtch Havlíek et al, Supervised Learning with Quantum-enhanced Feature Spaces (Quantum Kernel Methods).
3. Edward Farhi and Hartmut Neven, Research work on Quantum Neural Networks and Quantum Circuits.