Machine Learning-Based Optimization of Physical Layer Quantization for Diabetic Retinopathy Detection
Data used for this project can be accessed via https://www.kaggle.com/c/diabetic-retinopathy-detection Early detection of Diabetic Retinopathy helps slow down the progression to vision impairment. Machine learning-based medical image recognition and classification could effectively satisfy such demand. Physical layer optimization is essential for the overall CNN performance. In this final project, we reported a CNN model with a quantization-optimized physical layer that enables DR severity classification tasks with high accuracy.
