Neural Networks simulate the human brain's structure and function to create a machine-learning model. It is built with multiple layers (input, hidden, and output) of interconnected nodes called neurons and is trained on data sets to learn patterns of data. Neural Networks can be applied in various fields, such as image recognition, natural language processing, self-driving vehicles, anomaly detection, and Robotics.
Quantum Neural Networks (QNNs) are the quantum computing substitutes for conventional neural networks. They use quantum physics concepts to execute specific tasks more efficiently than their classical equivalents. QNNs are built to handle and analyze quantum data and may be used for tasks such as quantum state preparation, quantum pattern recognition, and quantum machine learning. They use quantum gates and quantum circuits to compute quantum bits (qubits) rather than conventional bits. QNN training may use quantum gradient descent or quantum variational algorithms.
In this section, we will discuss how the "Phishing" Dataset is used for the Quantum Neural Networks (QNN) model and the preprocessing techniques used to clean and transform the data in the dataset.
Learning objectives: after completing this module, students will be able to
(i) describe Quantum Neural Networks (QNN) and their applications
(ii) learn to preprocess the "Phishing" Dataset for QNN
(iii) apply the knowledge learned in this module to analyze more data sets using QNN