digantkumar/Text-Reconstruction-Deep-Learning- digantkumar/Text-Reconstruction-Deep-Learning-

  • Stars
    star
    1
  • Language
    Jupyter Notebook
  • Created over 4 years ago
  • Updated over 4 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
digantkumar/Text-Reconstruction-Deep-Learning-
github

digantkumar

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

• Extensions to Basic Autoencoder: Generated results for three different Dense and two different CNN architectures and compared their performance and summarized the impact of the architectures on performance. • Denoising Autoencoder: Generated complex CNN and ANN models to remove noise from an image and summarized the results using accuracy and clear predicted images. • Text Reconstruction: Generated complex CNN and ANN text reconstruction models from scratch, comparing their performances, accuracy and predicted images and generated a detailed report on the same.

More Repositories

1

Generalized-Linear-Modelling-Project

Conducted Preliminary Analysis on the given raw data by visualizing the trends and interpreted the variables with respect to the response variable. Fitted generalized linear models, starting from the null model to the final model and checked if the fitted model is adequate or not. Conducted diagnostics tests by checking for high leverage, high influential, outliers, sparsity and over dispersion in the given data. Generated a detail-oriented report on the same and explained the findings in layman terms.
R
1
star
2

Tic-Tac-Toe

Program which allows the user to play tic tac toe via user interactions
Python
1
star
3

Text-Classification-Machine-Learning-

Applied the state-of-the-art machine learning techniques namely KNN, Naïve Bayes, Decision Trees, Random Forest, Support Vector Machines, Cross Validation on a manually created bag of words from a raw folder and summarized the result of all the various techniques before and after hyper parameter tuning and generated a report on the same using performance metrics.
R
1
star