Masakhane Web Platform

The project funded by Mozilla Open Source Support Awards to create a web platform simillar to Google translate but for sollenli the African Languages that were made available by the masakhane community.

Masakhane Initiative

The project consist of putting African researchers from ACROSS the continent together to join the effort in building translation models for African languages. Masakhane means “We Build Together” in isiZRNNulu and was inspired by the Deep Learning Indaba theme for 2018. As part of the team, I’m working on Tshiluba.

|| || project page || || Github ||

A CNN Based Dog Breed Classifier In this project, I defined a Convolutional Neural Network that performs better than the average human when given the task of identifying dog breeds in addition, if supplied an image of a human, the code will also produce an estimate of the closest-resembling dog breed.

|| || Github ||

A RNN Based Model : Generate TV Scripts Implemented an RNN to generate my own Seinfeld TV scripts using RNNs. I used part of the Seinfeld dataset of scripts from 9 seasons. Using RNN, I generated a new, “fake” TV script, based on patterns it recognizes in this training data.

|| || Github ||

Generate Faces Generating images of the face using Deep Convolutional Generative Adversarial Network (DCGAN). The DCGAN is made of a pair of multilayer neural networks that compete against each other until one learns to generate realistic images of faces

|| || Github ||