Artificial Intelligence
AI is the discipline that deals with uncertainty and manages it in decision making. Peter Norvig
AI program is called Intelligent Agent just like AlphaGo. You can learn more about AlphaGo by watching the documentary and/or reading the paper.
This repository is built to showcase completed classroom projects of Artificial Intelligence and Specializations Nanodegree offered by Udacity
This README is broken down into the following sections:
- Sudoku
- Isolation
- Planning
- Recognizer
- Computer Vision Capstone
- Natural Language Processing Capstone
- Voice User Interface Capstone
Sudoku
In this project we practiced two very important concepts of artificial intelligence, constraint propagation and search. We created an AI agent that will solve any Sudoku puzzle. In this project, The goals are to implement the naked twins function, and write an AI agent that will solve the Diagonal Sudoku game.The algorithm fully used are based from the great blogpost of Peter Norvig.
You can find more information about the implementation steps of this project on the project’s own README file. Also, You can visit the project’s original repository for further information.
My Solution
Isolation
In this project, we implemented
- minimax search
- minimax search with alpha-beta pruning
- iterative deepening search
- our own best position evaluation heuristic
- our own alternate position evaluation heuristic
- our own alternate position evaluation heuristic
In the second part of this project we read a seminal paper in the field of Game-Playing and wrote a simple one page summary on it. In my case I read AlphaGo paper.
You can find more information about the implementation steps of this project on the project’s own README file. Also, You can visit the project’s original repository for further information.
My Solution
Planning
In this project, we defined a group of problems in classical PDDL (Planning Domain Definition Language) for the air cargo domain discussed in the lectures. then we set up the problems for search, experiment with various automatically generated heuristics, including planning graph heuristics, to solve the problems, and then we provided an analysis of the results. Additionally, we wrote a short research review paper on the historical development of planning techniques and their use in artificial intelligence.
You can find more information about the implementation steps of this project on the project’s own README file. Also, You can visit the project’s original repository for further information.
My Solution
Recognizer
In this project, we built a system that can recognize words communicated using the American Sign Language (ASL). We were provided a preprocessed dataset of tracked hand and nose positions extracted from video. Our goal was to train a set of Hidden Markov Models (HMMs) using part of this dataset to try and identify individual words from test sequences.
As an optional challenge, we incorporated Statistical Language Models (SLMs) that capture the conditional probability of particular sequences of words occurring. This helped us improve the recognition accuracy of your system.
You can find more information about the implementation steps of this project on the project’s own README file. Also, You can visit the project’s original repository for further information.
My Solution
- ASL Recognizer Solution Notebook
- Model Selector Solution
- Recognizer Solution
Computer Vision Capstone
In this project, we combinec our knowledge of computer vision techniques and deep learning to build and end-to-end 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. Our completed code can take in any image containing faces and identify the location of each face and their facial keypoints.
You can find more information about the implementation steps of this project on the project’s own README file. Also, You can visit the project’s original repository for further information.
My Solution
Natural Language Processing Capstone
In this project, you built 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.
You can find more information about the implementation steps of this project on the project’s own README file. Also, You can visit the project’s original repository for further information.
My Solution
Voice User Interface Capstone
In this project, we built a deep neural network that functions as part of an end-to-end automatic speech recognition (ASR) pipeline!
We begin by investigating the LibriSpeech dataset that will be used to train and evaluate our models. Our algorithm will first convert any raw audio to feature representations that are commonly used for ASR. Then we moved on to building neural networks that can map these audio features to transcribed text. After learning about the basic types of layers that are often used for deep learning-based approaches to ASR, we engaged in our own investigations by creating and testing our own state-of-the-art models.
You can find more information about the implementation steps of this project on the project’s own README file. Also, You can visit the project’s original repository for further information.
My Solution