My completed projects from Udacity's Machine Learning Engineer Nanodegree
My Nanodegree certificate: https://graduation.udacity.com/confirm/EGH7NNKR
Directory: capstone
Predicting churning customers in the telco industry from customer demographic, financial, and usage data.
- Data quality analysis
- Exploratory data analysis
- Data cleaning / data transformation
- Model building and model selection
- Model performance evaluation
Directory: dog_project
Given an image of a dog, the algorithm will identify an estimate of the canine’s breed. If supplied an image of a human, the code will identify the resembling dog breed.
- Deep learning
- Convolutional neural nets
- Transfer learning
- Keras / tensorflow
Repository: https://github.com/manuelseeger/RL-Quadcopter-2
Teach a quadcopter how to fly with reinforcement learning. Includes implementations of DDPG agents for the quadcopter environment and the mountaincar-continuous environment.
- Deep reinforcement learning
- Actor-critic methods
- Deep Q-learning, DDPG
- Experiment design and management
Directory: customer_segments
Customer segmentation based on buying behavior. Segment customers into clusters based on their purchases.
- Data transformation, outlier removal
- Clustering: KNN, Gaussian mixture models
- Principal component analysis
Directory: finding_donors
- Data quality analysis
- Exploratory data analysis
- Data cleaning / data transformation
- Model building and model selection
- Model performance evaluation