There are 1 repository under overfitting-reduced topic.
[MICCAI2019 & TMI2020] Overfitting under Class Imbalance: Anaylsis and Improvements for Medical Image Segmentation.
Dropout in Deep Learning
Classification of signatures in image format as genuine or fake. Created two models - one from scratch using deep learning layers and other using pre trained model VGG16. Before training used image pre processing techniques as well.
This project demonstrates the use of multi-class SVM on the Adult Census Income dataset from the UCI Machine Learning Repository. T
The model uses CNNs to guess the flower in the image. At each epoch, the model's neurons undergo a random dropout and the data is augmented. Overfitting is eliminated. The dataset can be downloaded storage.googleapis.com/download/example_images/flower_photos.tgz.
Health Profile Analysis:Revealing Disorder Paterns,Medication Guidance and Risk Classification-ML Project
This project explores the working of various Boosting algorithms and analyzes the results across different algorithms. Algorithms Used are: Random Forest, Ada Boost, Gradient Boost and XG Boost
This is the dataset used in the second chapter of Aurélien Géron's recent book 'Hands-On Machine learning with Scikit-Learn and TensorFlow'. It serves as an excellent introduction to implementing machine learning algorithms because it requires rudimentary data cleaning, has an easily understandable list of variables and sits at an optimal size between being to toyish and too cumbersome.