Paper Title
A Preliminary Study On Small Scale Quantum Neural Network Simulation Using Numpy

Abstract
This paper presents a basic, small-scale implementation of a Quantum Neural Network (QNN) using only NumPy. The objective is to demonstrate quantum-inspired learning concepts in a pedagogical and resource-efficient manner. The model employs a two-qubit circuit, with RY rotation gates for data encoding and a CNOT gate to introduce entanglement. Classical input data are projected into quantum states, and measurement probabilities are mapped to binary class predictions. The model is trained on the Breast Cancer Wisconsin dataset using the parameter-shift rule and gradient descent optimization. Despite its simplicity and execution on limited classical hardware, the QNN achieves over 80% accuracy, confirming that meaningful learning is possible even with minimal architectures. This approach offers a foundational framework for teaching and exploring quantum-enhanced learning concepts. Keywords - Quantum Neural Networks (QNN), NumPy, RY gate, CNOT gate, Quantum Machine Learning.