View Code? Open in Web Editor
NEW
Learning Data Science, ML models, Deep Learning, ANNs, CNNs nd RNNs through projects
Jupyter Notebook 99.92%
Python 0.08%
ml-projects's Introduction
- Data Visualization
- Prediction of Confirmed cases of various countries (just basic implementation)
- trained MNIST dataset on Neural Network with one hidden layer of 128 neurons
- using Loss Function: sparse categorical crossentropy, optimizer: Adam
- attaining an accuracy of ~98%
- develop the neural network from scratch
- Best accuracy of 80%
- Image CLassification of Flowers
- used concept of Transfer Learning
- can attain accuracy of ~99%
- worked on fashion_mnist dataset
- implemented CNNs
- can attain accuracy of ~92.8%
- also tried to implement on CIFAR-10 dataset
- can be deployed as application for fae verification
- used Siamese network
- used imdb reviews dataset
- implemented RNNs from scratch (vocabulary intialization, embedding, RNN architecture, training & updating parameters, Prediction)
ml-projects's People
Contributors
Watchers