GitHub - bhawna759/QRisers-Conspicious-QML: Experimented with Convolution, Pooling, ImageGenerator using Tensorflow on MNIST dataset

**Solution is submitted as assignment in Womanium Quantum 2024 **

Project : QML for Conspicuity Detection

QRisers Conspicious Team members

Final Codes Submitted:

Analysis of Model Performance on MNIST Dataset

Performance Comparison: The graph comparing the Quantum Neural Network (QNN) and Convolutional Neural Network (CNN) models on the MNIST dataset reveals that the QNN exhibits a significantly lower loss function value. This indicates that the QNN achieves better performance with reduced error compared to the CNN.
Training Efficiency: Additionally, the QNN reaches higher accuracy in fewer epochs, whereas the CNN requires more epochs to achieve comparable accuracy. This suggests that the QNN is not only more efficient but also potentially more effective in terms of training time, demonstrating its superior utility over the CNN for this particular task.

Name		Name	Last commit message	Last commit date
Latest commit History 29 Commits
Building LLM promts with variables.ipynb		Building LLM promts with variables.ipynb
Creating Neural Network in JAX - MNIST.ipynb		Creating Neural Network in JAX - MNIST.ipynb
Creating_a_neural_network_in_JAX - v2.ipynb		Creating_a_neural_network_in_JAX - v2.ipynb
Final QNN_VS_Classical_MNIST_tensorflow.ipynb		Final QNN_VS_Classical_MNIST_tensorflow.ipynb
JAX Code for CNN in python for quantum computing.ipynb		JAX Code for CNN in python for quantum computing.ipynb
JAX Code in python for classical cnn, using MNIST dataset.ipynb		JAX Code in python for classical cnn, using MNIST dataset.ipynb
MNIST Classification using Tensorflow.ipynb		MNIST Classification using Tensorflow.ipynb
QNN VS Classical MNIST tensorflow .ipynb		QNN VS Classical MNIST tensorflow .ipynb
QNN-MNIST-Tensorflow.ipynb		QNN-MNIST-Tensorflow.ipynb
QNN_MNIST.ipynb		QNN_MNIST.ipynb
README.md		README.md
SINE_FUNCTION_QML.ipynb		SINE_FUNCTION_QML.ipynb

Provide feedback