In this exercise you will explore Constraint Satisfaction Problems in a Jupyter notebook and use a CSP solver to solve a variety of problems.
Read more here
Please DO NOT publish your work on this exercise.
In this exercise you will teach Pac-Man to search his world to complete the following tasks:
- find a single obstacle
- find multiple obstacles
- find the fastest way to eat all the food in the map
In this exercise, you'll implement several local search algorithms and test them on the Traveling Salesman Problem (TSP) between a few dozen US state capitals.
Read more here
In this project, you will extend the Sudoku-solving agent developed in the classroom lectures to solve diagonal Sudoku puzzles and implement a new constraint strategy called "naked twins". A diagonal Sudoku puzzle is identical to traditional Sudoku puzzles with the added constraint that the boxes on the two main diagonals of the board must also contain the digits 1-9 in each cell (just like the rows, columns, and 3x3 blocks).
Read more here
This project is split between implementation and analysis. First you will combine symbolic logic and classical search to implement an agent that performs progression search to solve planning problems. Then you will experiment with different search algorithms and heuristics, and use the results to answer questions about designing planning systems.
Read more here
In this project you will choose an experiment with adversarial game-playing techniques like minimax, Monte Carlo tree search, opening books, and more. Your goal will be to build and evaluate the performance of your agent in a finite deterministic two player game of perfect information called Isolation.
Read more here
In this notebook, you'll use the Pomegranate library to build a hidden Markov model for part of speech tagging with a universal tagset. Hidden Markov models have been able to achieve >96% tag accuracy with larger tagsets on realistic text corpora. Hidden Markov models have also been used for speech recognition and speech generation, machine translation, gene recognition for bioinformatics, and human gesture recognition for computer vision, and more.
Read more here
Read more here
Welcome to the Convolutional Neural Networks (CNN) project in the AI Nanodegree! In this project, you will learn how to build a pipeline that can be used within a web or mobile app to process real-world, user-supplied images. Given an image of a dog, your 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.
Along with exploring state-of-the-art CNN models for classification, you will make important design decisions about the user experience for your app. Our goal is that by completing this lab, you understand the challenges involved in piecing together a series of models designed to perform various tasks in a data processing pipeline. Each model has its strengths and weaknesses, and engineering a real-world application often involves solving many problems without a perfect answer. Your imperfect solution will nonetheless create a fun user experience!
Read more here
Recurrent Neural Networks course project: time series prediction and text generation
Read more here
Read more here
A simple question-answering system built using IBM Watson's NLP services.
In this project, you will use IBM Watson's NLP Services to create a simple question-answering system. You will first use the Discovery service to pre-process a document collection and extract relevant information. Then you will use the Conversation service to build a natural language interface that can respond to questions.
Read more here
In this notebook, you will build a deep neural network that functions as part of an end-to-end machine translation pipeline. Your completed pipeline will accept English text as input and return the French translation.
Read more here