These are a collection of projects done for Udacity Artificial Intellience Nanadegree and Deep Learning Nanodegree.
This project build a deep neural network that functions as part of an end-to-end automatic speech recognition pipeline.
STEP 1: Acoustic Features for Speech Recognition STEP 2: Deep Neural Networks for Acoustic Modeling
Model 0: RNN
Model 1: RNN + TimeDistributed Dense
Model 2: CNN + RNN + TimeDistributed Dense
Model 3: Deeper RNN + TimeDistributed Dense
Model 4: Bidirectional RNN + TimeDistributed Dense
Models 5+
Compare the Models
Final Model
STEP 3: Obtain Predictions
In this project, we combine computer vision techniques and deep learning to build and end-to-end facial keypoint recognition system. Facial keypoints include points around the eyes, nose, and mouth on any face and are used in many applications, from facial tracking to emotion recognition.
There are three main parts to this project:
Part 1 : Investigating OpenCV, pre-processing, and face detection
Part 2 : Training a Convolutional Neural Network (CNN) to detect facial keypoints
Part 3 : Putting parts 1 and 2 together to identify facial keypoints on any image.
In this project we build a deep neural network that functions as part of an end-to-end machine translation pipeline. The completed pipeline will accept English text as input and return the French translation.
Preprocess - You'll convert text to sequence of integers.
Models Create models which accepts a sequence of integers as input and returns a probability distribution over possible translations. After learning about the basic types of neural networks that are often used for machine translation, you will engage in your own investigations, to design your own model!
Prediction Run the model on English text.
In this project, you'll classify images from the CIFAR-10 dataset. The dataset consists of airplanes, dogs, cats, and other objects. You'll preprocess the images, then train a convolutional neural network on all the samples. The images need to be normalized and the labels need to be one-hot encoded. You'll get to apply what you learned and build a convolutional, max pooling, dropout, and fully connected layers. At the end, you'll get to see your neural network's predictions on the sample images.
In this project, we use generative adversarial networks to generate new images of faces.
In this project, we train a sequence to sequence model on a dataset of English and French sentences that can translate new sentences from English to French; this is done in TensorFlow whereas AIND Machine Translation is done in Keras.
In this project, we generate your own Simpsons TV scripts using RNNs. We us part of the Simpsons dataset of scripts from 27 seasons. The Neural Network we build will generate a new TV script for a scene at [Moe's Tavern].