Category: ml

Posts

There aren't any blog posts in this category, yet.

Projects

Analyzing NYC subway dataset ml udacity

A statistical analysis of the New York City subway passenger behavior.

Identifying fraud from Enron emails and financial data ml udacity

Using text mining and machine learning to build a “person of interest” classifier.

Training a smart cab how to drive ml udacity rl

A reinforcement learning agent using Q-learning to learn how to intelligently drive a cab in a 2D grid world with other agents.

Supervised learning survey ml gt python sklearn

Application and optimization of several supervised learning algorithms on two different classification problems and datasets.

Randomized optimization survey ml

Application and tuning of randomized optimization algorithms (randomized hill-climbing, simulated annealing, genetic algorithms, and MIMIC) on four classical problems (Traveling Salesman, Four Peaks, Knapsack, and ANN optimization).

Unsupervised learning survey ml

Application and optimization of unsupervised learning and dimensionality reduction algorithms (k-means clustering, expectation-maximization, PCA, ICA, and randomized projections) across the same two datasets from the previous supervised learning survey.

Reproducing Sutton 1988 ml gt rl

A reproduction of experimental results of Learning to Predict by Methods of Temporal Difference Learning (Sutton 1988).

Lunar lander ml gt rl

A reinforcement learning agent using Deep Q-networks (DQN) to control a lunar lander (OpenAI).

Reproducing Greenwald 2003 ml gt rl

A reproduction of experimental results of Correlated Q-learning (Greenwald 2003).

Bipedal walker ml rl

Implemented a reinforcement learning agent using Deep Deterministic Policy Gradients (DDPG) to learn how to control a bipedal walker (OpenAI).