1

Nanodegree key: nd009t

Version: 2.0.0

Locale: en-us

Become a machine learning engineer and apply predictive models to massive data sets in fields like education, finance, healthcare or robotics.

Content

Part 01 : Machine Learning Foundations

In this term, you’ll begin by exploring core machine learning concepts, before moving on to supervised and unsupervised learning.

Module 01: Introduction to the Nanodegree
- Lesson 01: Welcome to Machine Learning
  Welcome to Term 1 of the Machine Learning Nanodegree program!
- Lesson 02: What is Machine Learning?
  Explore some of the many machine learning concepts in just a few bite-sized lectures!
- Lesson 03: Introductory Practice Project
  In this practice project, you will create decision functions that attempt to predict survival outcomes from the 1912 Titanic disaster based on each passenger’s features, such as sex and age.
Module 02: Careers Services Orientation
- Lesson 01: Nanodegree Career Services
  The Careers team at Udacity is here to help you move forward in your career - whether it's finding a new job, exploring a new career path, or applying new skills to your current job.
  - Concept 01: Access the Career Portal
  - Concept 02: Prepare for the Udacity Talent Program
Module 03: How to Get Help from Peers and Mentors
- Lesson 01: Get Help with Your Account
  What to do if you have questions about your account or general questions about the program.
Module 04: Practice Assessment
- Lesson 01: NumPy and pandas Assessment
  Test your NumPy and pandas skills with a quick assessment.
  - Concept 01: Assessment
Module 05: Training and Testing Models
- Lesson 01: Training and Testing Models
  Learn to train and test models with NumPy and Pandas.
Module 06: Evaluation Metrics
- Lesson 01: Evaluation Metrics
  Learn the main metrics to evaluate models, such as accuracy, precision, recall, and more!
Module 07: Detecting and Fixing Errors
- Lesson 01: Model Selection
  Learn the main types of errors that can occur during training, and several methods to deal with them and optimize your machine learning models.
Module 08: Practice Assessment
- Lesson 01: Model Evaluation and Validation Assessment
  Test your Model Evaluation and Validation concepts with a quick assessment.
  - Concept 01: Model Evaluation and Validation assessment
Module 09: Predicting Housing Prices
- Lesson 01: Predicting Boston Housing Prices
  Put all you've learned into practice by building and optimizing a model to predict housing prices!
  
  Project Description - Predicting Boston Housing Prices
  
  Project Rubric - Predicting Boston Housing Prices
Module 10: Supervised Learning
- Lesson 01: Linear Regression
  Linear regression is a very effective algorithm to predict numerical data.
- Lesson 02: Perceptron Algorithm
  The perceptron algorithm is an algorithm for classifying data. It is the building block of neural networks.
- Lesson 03: Decision Trees
  Decision trees are a structure for decision-making where each decision leads to a set of consequences or additional decisions.
- Lesson 04: Naive Bayes
  Naive Bayesian Algorithms are powerful tools for creating classifiers for incoming labeled data.
- Lesson 05: Support Vector Machines
  Support vector machines are very effective models used for classification.
- Lesson 06: Ensemble Methods
  Bagging and boosting are two common ensemble methods for improving the accuracy of supervised learning approaches.
- Lesson 07: Supervised Learning Assessment
  Test your Supervised Learning concepts with a quick assessment.
  - Concept 01: Supervised Learning Assessment
- Lesson 08: Supervised Learning Project
  You've covered a wide variety of methods for performing supervised learning -- now it's time to put those into action!
  
  Project Description - Finding Donors for CharityML
  
  Project Rubric - Finding Donors for CharityML
Module 11: Clustering
- Lesson 01: Clustering
  Clustering is one of the most common methods of unsupervised learning. Here, we'll discuss the K-means clustering algorithm.
- Lesson 02: Clustering Mini-Project
  In this mini-project, you will use K-means to cluster movie ratings and use those clusters to provide movie recommendations.
- Lesson 03: Hierarchical and Density-based Clustering
  We continue to look at clustering methods. Here, we'll discuss hierarchical clustering and density-based clustering (DBSCAN).
- Lesson 04: Gaussian Mixture Models and Cluster Validation
  In this lesson, we discuss Gaussian mixture model clustering. We then talk about the cluster analysis process and how to validate clustering results.
Module 12: Feature Scaling
- Lesson 01: Feature Scaling
  Feature scaling is an important pre-processing step when performing unsupervised learning to allow multiple features to be analyzed together.
Module 13: Dimensionality Reduction
- Lesson 01: PCA
  PCA, principal component analysis, is a method for feature selection that turns a set of correlated variables into the underlying set of orthogonal variables.
Module 14: PCA Mini-Project
- Lesson 01: PCA Mini-Project
  In this mini-project, you'll apply principal component analysis to facial recognition.
  - Concept 01: PCA Mini-Project
Module 15: Random Projection and ICA
- Lesson 01: Random Projection and ICA
  In this lesson, we will look at two methods for feature extraction and dimensionality reduction: Random Projection and Independent Component Analysis (ICA)
Module 16: Unsupervised Learning Assessment
- Lesson 01: Unsupervised Learning Assessment
  Test your understanding of unsupervised learning with a quick assessment.
  - Concept 01: Assessment
Module 17: Unsupervised Learning Project
- Lesson 01: Creating Customer Segments
  Use unsupervised learning techniques to see if any similarities exist between customers and use those similarities to segment customers into distinct categories using various clustering techniques.
  
  Project Description - Creating Customer Segments
  
  Project Rubric - Creating Customer Segments
Module 18: Congratulations!
- Lesson 01: Congratulations!
  You've now reached the end of this program!
  - Concept 01: Congratulations!

Part 02 : Advanced Machine Learning

In this term, you’ll cover topics in deep learning and reinforcement learning. The term will culminate with a capstone project of your choosing, that applies the machine learning techniques and algorithms you have learned.

Module 01: Introduction to the Nanodegree
- Lesson 01: Welcome to Advanced Machine Learning
  Welcome to Term 2 of the Machine Learning Nanodegree program!
Module 02: Deep Learning
- Lesson 01: Neural Networks
  Luis will give you an overview of logistic regression, gradient descent, and the building blocks of neural networks.
- Lesson 02: Cloud Computing
  Take advantage of Amazon's GPUs to train your neural network faster. In this lesson, you'll setup an instance on AWS and train a neural network on a GPU.
- Lesson 03: Deep Neural Networks
  A deeper dive into backpropagation and the training process of neural networks, including techniques to improve the training.
- Lesson 04: Convolutional Neural Networks
  Alexis explains the theory behind Convolutional Neural Networks and how they help us dramatically improve performance in image classification.
- Lesson 05: Deep Learning for Cancer Detection with Sebastian Thrun
  In this lesson, Sebastian Thrun teaches us about his groundbreaking work detecting skin cancer with convolutional neural networks.
- Lesson 06: Deep Learning Assessment
  Test your Deep Learning concepts with a quick assessment.
  - Concept 01: Assessment
- Lesson 07: Deep Learning Project
  In this project, you will learn how to build a pipeline to process real-world, user-supplied images.
  
  Project Description - Dog Breed Classifier
  
  Project Rubric - Dog Breed Classifier
  - Concept 01: Dog Breed Recognition Project
  - Concept 02: Dog Breed Workspace
Module 03: Reinforcement Learning
- Lesson 01: Introduction to RL
  Reinforcement learning is a type of machine learning where the machine or software agent learns how to maximize its performance at a task.
- Lesson 02: The RL Framework: The Problem
  Learn how to mathematically formulate tasks as Markov Decision Processes.
- Lesson 03: The RL Framework: The Solution
  In reinforcement learning, agents learn to prioritize different decisions based on the rewards and punishments associated with different outcomes.
- Lesson 04: Dynamic Programming
  The dynamic programming setting is a useful first step towards tackling the reinforcement learning problem.
- Lesson 05: Monte Carlo Methods
  Write your own implementation of Monte Carlo control to teach an agent to play Blackjack!
- Lesson 06: Temporal-Difference Methods
  Learn about how to apply temporal-difference methods such as Sarsa, Q-Learning, and Expected Sarsa to solve both episodic and continuous tasks.
- Lesson 07: Solve OpenAI Gym's Taxi-v2 Task
  With reinforcement learning now in your toolbox, you're ready to explore a mini project using OpenAI Gym!
Module 04: Deep Reinforcement Learning
- Lesson 01: RL in Continuous Spaces
  Review the fundamental concepts of reinforcement learning, and learn how to adapt traditional algorithms to work with continuous spaces.
- Lesson 02: Deep Q-Learning
  Extend value-based reinforcement learning methods to complex problems using deep neural networks.
- Lesson 03: Policy-Based Methods
  Policy-based methods try to directly optimize for the optimal policy. Learn how they work, and why they are important, especially for domains with continuous action spaces.
- Lesson 04: Actor-Critic Methods
  Learn how to combine value-based and policy-based methods, bringing together the best of both worlds, to solve challenging reinforcement learning problems.
- Lesson 05: Teach a Quadcopter How to Fly
  Build a quadcopter flying agent that learns to take off, hover and land using reinforcement learning.
  
  Project Description - Teach a Quadcopter How to Fly
  
  Project Rubric - Teach a Quadcopter How to Fly
Module 05: Practice Assessment
- Lesson 01: Reinforcement Learning Assessment
  Test your understanding of reinforcement learning with a quick assessment.
  - Concept 01: Assessment
Module 06: Career Support
- Lesson 01: Optimize Your GitHub Profile
  Other professionals are collaborating on GitHub and growing their network. Submit your profile to ensure your profile is on par with leaders in your field.
  
  Project Description - Optimize Your GitHub Profile
  
  Project Rubric - Optimize Your GitHub Profile
- Lesson 02: Take 30 Min to Improve your LinkedIn
  Find your next job or connect with industry peers on LinkedIn. Ensure your profile attracts relevant leads that will grow your professional network.
  
  Project Description - Improve Your LinkedIn Profile
  
  Project Rubric - Improve Your LinkedIn Profile
Module 07: Capstone Proposal
- Lesson 01: Writing up a Capstone Proposal
  Before working on a machine learning problem, write up a proposal of your project to get valuable feedback!
  
  Project Description - Capstone Proposal
  
  Project Rubric - Capstone Proposal
Module 08: Capstone Project
- Lesson 01: Machine Learning Capstone Project
  Now you will put your Machine Learning skills to the test by solving a real world problem using the algorithms you have learned in the program so far.
  
  Project Description - Capstone Project
  
  Project Rubric - Capstone Project

**Part 03 (Elective):** Extracurricular: Deep Learning - Tensor Flow

Module 01: Machine Learning to Deep Learning
- Lesson 01: Software and Tools
  How to setup TensorFlow and fetch assignment starter code
  - Concept 01: TensorFlow
- Lesson 02: Deep Learning
  Now that you've been exposed to various types of learning (supervised, unsupervised, and reinforcement), it's time to get a deeper understanding of machine learning with deep learning!
Module 02: Intro to TensorFlow
- Lesson 01: Intro to TensorFlow
  In this lesson, we'll cover the basics of TensorFlow and how to get started creating a simple classifier using this library.
Module 03: Intro to Neural Networks
- Lesson 01: Intro to Neural Networks
  In this lesson, you'll dive deeper into the intuition behind Logistic Regression and Neural Networks. You'll also implement gradient descent and backpropagation in python right here in the classroom.
Module 04: Deep Neural Networks
- Lesson 01: Deep Neural Networks
  Vincent walks you through how to go from a simple neural network to a deep neural network. You'll learn about why additional layers can help and how to prevent overfitting.
Module 05: Convolutional Neural Networks
- Lesson 01: Convolutional Neural Networks
  Vincent explains the theory behind Convolutional Neural Networks and how they help us dramatically improve performance in image classification.

Content

Part 01 : Machine Learning Foundations

Part 02 : Advanced Machine Learning

Part 03 (Elective): Extracurricular: Deep Learning - Tensor Flow

**Part 03 (Elective):** Extracurricular: Deep Learning - Tensor Flow