Projects developed during Udacity's Artificial Intelligence Nanodegree.
-
Term 2 - Deep Learning
-
Term 1 - Artificial Intelligence Fundamentals
Built an end-to-end real-time 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.
Keywords: Convolutional Neural Networks, Facial Keypoint Detection, OpenCV.
Built RNNs that can generate sequences based on input data - with a focus on two applications: used real market data in order to predict future Apple stock prices using an RNN model. The second one was be trained on Sir Arthur Conan Doyle's classic novel Sherlock Holmes to generates wacky sentences based on it.
Keywords: Recurrent Neural Networks, Time Series, Natural Language Processing.
Applied Data Augmentation and Transfer Learning to create a CNN-based application to classify 133 different dog breeds with 87.42% accuracy.
Keywords: Deep Convolutional Neural Networks, Transfer Learning
Analysed a dataset of 50,000 movie reviews from IMDB and used it to predict the sentiment of a review.
Keywords: Sentiment Analysis, Natural Language Processing, Neural Networks
Built a system that can recognize words communicated using the American Sign Language (ASL). Trained a set of Hidden Markov Models (HMMs) using part of a preprocessed dataset of tracked hand and nose positions extracted from video to try and identify individual words from test sequences. Experimented with model selection techniques including BIC, DIC, and K-fold Cross Validation.
Keywords: Probabilistic Graphical Models, Model Selection
Used logic and planning techniques to create an AI that finds the most efficient route to route cargo around the world to their respective destinations. This project used a combination of propositional logic and search along with A* heuristics to find optimal planning solutions.
Keywords: Logic, Planning, Search
Created an AI that beats human opponents in the game of Isolation using Minimax, Alpha-Beta Search, and Iterative Deepening.
Keywords: Game Playing, Search
Created an AI to solve Diagonal Sudokus using constraint propagation and search techniques. Additionally, taught the agent to use the Naked Twins advanced Sudoku strategy.
Keywords: Constraint Propagation, Search