• Implemented graph search algorithms such as BFS, DFS, Dijkstra’s, and A-star algorithms and heuristics

• Implemented Pac-Man agents using machine learning, A* search, alpha-beta minimax, and expectimax techniques.

• Programmed reinforcement learning algorithms such as value iteration and Q-learning.

• Implemented the perceptron algorithm and gradient descent, which were used to train neural network classifiers. Trained a convolutional neural network to learn better features on a set of scanned handwritten digit images.

Link to Project 1 - Search - http://ai.berkeley.edu/search.html

Link to Project 2 - Multiagent - http://ai.berkeley.edu/multiagent.html

Link to Project 3 - Reinforcement - http://ai.berkeley.edu/reinforcement.html

Link to Project 4 - Deep Learning with Tensorflow - https://edge.edx.org/courses/course-v1:BerkeleyX+CS188x-SP16+SP16/

To access project 4:

1. Sign in to EDX

2. Select the CS188x course 

3. Click Course tab 

4. Under Week 14, click Project 6: Classification