These are my five projects implemented during the Udacity Deep Learning Nanodegree Program.
Course completion link here
In this project, a neural network from scratch ia built to carry out a prediction problem on a
Bike Sharing Dataset.You can access the data set from here: Bike Sharing Dataset Data Set
https://archive.ics.uci.edu/ml/datasets/Bike+Sharing+Dataset
The notebook link here
Model prediction on the test dataset was:
In this project, I built a pipeline to process real-world, user-supplied images. Given an image of a dog, our algorithm will identify an estimate of the canine’s breed.
If supplied an image of a human face, the code will identify the resembling dog breed.
Note book link here
Model prediction on the human and dog images is:
In this project, I generated my own Seinfeld TV scripts using RNNs.
I used a Seinfeld dataset of scripts from 9 seasons. The Neural Network I built generated a new, "fake" TV script.
Note book link here
TV sripts generated by the model:
In this project, I used generative adversarial networks (GANs) to generate new images of faces.
Notebook link here
Face generated by the model
In this project, I constructed a recurrent neural network for the purpose of determining the sentiment of a movie review using the IMDB data set. I created this model using Amazon's SageMaker service.
In addition, I deployed my model and construct a simple web app which interacts with the deployed model.
Notebook link here
