DeepsMoseli/Wells-Fargo-Campus-Analytics-Challenge-Natural-Language-Processing

Stars
1
Language
HTML
License
MIT License
Created almost 5 years ago
Updated almost 5 years ago

DeepsMoseli/Wells-Fargo-Campus-Analytics-Challenge-Natural-Language-Processing

DeepsMoseli

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

In this challenge, the goal is to use a hierarchical topic model for clustering the provided data.

Bidirectiona-LSTM-for-text-summarization-

A bidirectional encoder-decoder LSTM neural network is trained for text summarization on the cnn/dailymail dataset. (MIT808 project)

LSTMGAN-for-melody-generation

An LSTM GAN implementation for music generation from MIDI files. The work closely follows work on GAN hacks in https://github.com/soumith/ganhacks

Siamese-LSTM-on-sentence-similarity

Using Siamese LSTM to classify repeated quora questions. Attempted pretrained bert embeddings, Word2Vec and training own embeddings together with the model.

Jupyter Notebook

MLP-GA-hyperparameter-search

I Evolve an evolutionarry algorithm to optimize a sklearn MLP on the breast cancer dataset

Jupyter Notebook

detectron2-dormalarm

I use detectron2 to demonstrate a computer vision powered dorm room security system that leverages transfer learning.

Jupyter Notebook

Intro-to-reinforcement-learning

This is a simple Q table based reinforcement learning algorithm aimed to help you get started. The task is for the agent cross a river represented by a string of dashes. I did not want to focus on the display of the environment much so it isnt a good interface

MLP

implementation of a multi-layer perceptron

geneticml

This library uses genetic algorithms to for automated hyper-parameter optimization in Machine learning algorithms. this was done as my ICS674 evolutionary computation project

TswanaBert

TswanaBERT is a transformer model pre-trained on a corpus of Setswana language data in a self-supervised fashion. works in both pytorch and TF

Jupyter Notebook