1.Logistic_Regression:

We have implemented Logistic Regression classifier from the scratch in python. This is a multiclassification model where we have used OneVsAll to classify more than 2 target variables. Detail documentation can be viewed by my article on Medium.com https://medium.com/@aryamohapatra/logistic-regression-from-scratch-multi-classification-with-onevsall-d5c2acf0c37c

2.Deep Neural Network for Image classification (CIFAR Dataset):

Image recognition is one task now tackled with ML,that was considered “very hard” not long ago. Here we have built a Deep Neural network to classify the images of Dogs and Horses from CIFAR Dataset. We have used the CIFAR-10 dataset https://www.cs.toronto.edu/~kriz/cifar.html

• Each image is 32x32, 3 colour channels (RGB):Use just 1 colour or convert to greyscale;Convert to vector of 1024 floats
• 50k training images, 10k testing images: We have selected random subsets (e.g. 1 batch)