E0-250-Deep-Learning

E0 250 Deep Learning course is offered by Department of Computer Science and automation, Indian Institute of Science, Bangalore.

E0 250 Deep Learning, CSA, IISc Bangalore Solved Assignments for Jan 2020 Course

Fizzbuz

An integer divisible by 3 is printed as Fizz, and integer divisible by 5 is printed as Buzz. An integer divisible by both 3 and 5 is printed as FizzBuzz.

This assignment was implemented with logic and ML based model.

Fashion-MNIST clothing images

The Fashion-MNIST is a dataset of Zalando’s article images, consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes.

Implemented a MLP and a CNN on fashion-MNIST dataset.

Stanford Natural Language Inference(SNLI)

The SNLI corpus (version 1.0) is a collection of 570k human-written English sentence pairs manually labeled for balanced classification with the labels entailment, contradiction, and neutral, supporting the task of natural language inference (NLI), also known as recognizing textual entailment (RTE).

Implemented a LSTM and Logistic regression based model on SNLI.