Computer Vision Nanodegree v5.0.0

Nanodegree key: nd891

Version: 5.0.0

Locale: en-us

Master the computer vision skills behind advances in robotics and automation. Write programs to analyze images, implement feature extraction, and recognize objects using deep learning models.

Content

Part 01 : Introduction to Computer Vision

Module 01: Introduction to the Nanodegree
- Lesson 01: Welcome to Computer Vision
  
  Welcome to the Computer Vision Nanodegree program!
- Lesson 02: Knowledge, Community, and Careers
  
  You are starting a challenging but rewarding journey! Take 5 minutes to read how to get help with projects and content.
- Lesson 03: Get Help with Your Account
  
  What to do if you have questions about your account or general questions about the program.
  - Concept 01: FAQ
  - Concept 02: Support
- Lesson 04: Image Representation & Classification
  
  Learn how images are represented numerically and implement image processing techniques, such as color masking and binary classification.
- Lesson 05: Convolutional Filters and Edge Detection
  
  Learn about frequency in images and implement your own image filters for detecting edges and shapes in an image. Use a computer vision library to perform face detection.
- Lesson 06: Types of Features & Image Segmentation
  
  Program a corner detector and learn techniques, like k-means clustering, for segmenting an image into unique parts.
- Lesson 07: Feature Vectors
  
  Learn how to describe objects and images using feature vectors.
- Lesson 08: CNN Layers and Feature Visualization
  
  Define and train your own convolution neural network for clothing recognition. Use feature visualization techniques to see what a network has learned.
- Lesson 09: Project: Facial Keypoint Detection
  
  Apply your knowledge of image processing and deep learning to create a CNN for facial keypoint (eyes, mouth, nose, etc.) detection.
  
  Project Description - Facial Keypoint Detection
  
  Project Rubric - Facial Keypoint Detection
- Lesson 10: Jobs in Computer Vision
  
  Learn about common jobs in computer vision, and get tips on how to stay active in the community.
- Lesson 11: 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

Part 02 : Optional: Cloud Computing

Module 01: Optional: Cloud Computing
- Lesson 01: Cloud Computing with Google Cloud
  
  Learn how to leverage GPUs on Google Cloud for machine learning and scientific computing.

Part 03 : Advanced Computer Vision & Deep Learning

Module 01: Advanced Computer Vision and Deep Learning
- Lesson 01: Advanced CNN Architectures
  
  Learn about advances in CNN architectures and see how region-based CNN’s, like Faster R-CNN, have allowed for fast, localized object recognition in images.
- Lesson 02: YOLO
  
  Learn about the YOLO (You Only Look Once) multi-object detection model and work with a YOLO implementation.
- Lesson 03: RNN's
  
  Explore how memory can be incorporated into a deep learning model using recurrent neural networks (RNNs). Learn how RNNs can learn from and generate ordered sequences of data.
- Lesson 04: Long Short-Term Memory Networks (LSTMs)
  
  Luis explains Long Short-Term Memory Networks (LSTM), and similar architectures which have the benefits of preserving long term memory.
- Lesson 05: Hyperparameters
  
  Learn about a number of different hyperparameters that are used in defining and training deep learning models. We'll discuss starting values and intuitions for tuning each hyperparameter.
- Lesson 06: Optional: Attention Mechanisms
  
  Attention is one of the most important recent innovations in deep learning. In this section, you'll learn how attention models work and go over a basic code implementation.
- Lesson 07: Image Captioning
  
  Learn how to combine CNNs and RNNs to build a complex, automatic image captioning model.
- Lesson 08: Project: Image Captioning
  
  Train a CNN-RNN model to predict captions for a given image. Your main task will be to implement an effective RNN decoder for a CNN encoder.
  
  Project Description - Image Captioning
  
  Project Rubric - Image Captioning
- Lesson 09: 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

Part 04 : Object Tracking and Localization

Module 01: Object Tracking & Localization
- Lesson 01: Introduction to Motion
  
  This lesson introduces a way to represent motion mathematically, outlines what you'll learn in this section, and introduces optical flow.
- Lesson 02: Robot Localization
  
  Learn to implement a Bayesian filter to locate a robot in space and represent uncertainty in robot motion.
- Lesson 03: Mini-project: 2D Histogram Filter
  
  Write sense and move functions (and debug) a 2D histogram filter!
- Lesson 04: Introduction to Kalman Filters
  
  Learn the intuition behind the Kalman Filter, a vehicle tracking algorithm, and implement a one-dimensional tracker of your own.
- Lesson 05: Representing State and Motion
  
  Learn about representing the state of a car in a vector that can be modified using linear algebra.
- Lesson 06: Matrices and Transformation of State
  
  Linear Algebra is a rich branch of math and a useful tool. In this lesson you'll learn about the matrix operations that underly multidimensional Kalman Filters.
- Lesson 07: Simultaneous Localization and Mapping
  
  Learn how to implement SLAM: simultaneously localize an autonomous vehicle and create a map of landmarks in an environment.
- Lesson 08: Optional: Vehicle Motion and Calculus
  
  Review the basics of calculus and see how to derive the x and y components of a self-driving car's motion from sensor measurements and other data.
- Lesson 09: Project: Landmark Detection & Tracking (SLAM)
  
  Implement SLAM, a robust method for tracking an object over time and mapping out its surrounding environment, using elements of probability, motion models, and linear algebra.
  
  Project Description - Landmark Detection & Tracking (SLAM)
  
  Project Rubric - Landmark Detection & Tracking (SLAM)
  - Concept 01: Project Overview
  - Concept 02: Project: Landmark Detection & Tracking (SLAM)

**Part 05 (Elective) :** Applications of Computer Vision and Deep Learning

Take a quick look at a few really cool applications of deep learning and computer vision, such as Neural Style Transfer, that using pre-trained models.

Module 01: Applying Computer Vision and Deep Learning Models
- Lesson 01: Applying Deep Learning Models
  
  Try out a few really cool applications of computer vision and deep learning, such as style transfer, using pre-trained models that others have generously provided on Github.

**Part 06 (Elective) :** Review: Training A Neural Network

Review how neural networks turn an input into an output and how they monitor errors as they train. This section will also cover methods to avoid overfitting your data.

Module 01: How Neural Networks Train
- Lesson 01: Feedforward and Backpropagation
  
  Short introduction to neural networks: how they train by doing a feedforward pass then performing backpropagation.
- Lesson 02: Training Neural Networks
  
  Now that you know what neural networks are, in this lesson you will learn several techniques to improve their training.
- Lesson 03: Deep Learning with PyTorch
  
  Learn how to use PyTorch for building deep learning models

**Part 07 (Elective) :** Skin Cancer Detection

Learn how to utilize neural networks to distinguish between images of benign and cancerous skin tissue.

Module 01: Deep Learning for Cancer Detection
- Lesson 01: Deep Learning for Cancer Detection with Sebastian Thrun
  
  Sebastian Thrun teaches us about his groundbreaking work detecting skin cancer with convolutional neural networks.

**Part 08 (Elective) :** Text Sentiment Analysis

Learn how to create a simple neural network for analyzing the sentiment (bad or good) in the text of movie reviews.

Module 01: Sentiment Analysis
- Lesson 01: Sentiment Analysis
  
  In this lesson, Andrew Trask, the author of Grokking Deep Learning, will walk you through using neural networks for sentiment analysis.

**Part 09 (Elective) :** More Deep Learning Models

Module 01: Scene Understanding
- Lesson 01: Fully-Convolutional Neural Networks & Semantic Segmentation
  
  Get a high-level overview of how fully-convolutional neural networks work, and see how they can be used to classify every pixel in an image.

**Part 10 (Elective) :** C++ Programming

Module 01: C++ Basics
- Lesson 01: C++ Getting Started
  
  The differences between C++ and Python and how to write C++ code.
- Lesson 02: C++ Vectors
  
  To program matrix algebra operations and translate your Python code, you will need to use C++ Vectors. These vectors are similar to Python lists, but the syntax can be somewhat tricky.
- Lesson 03: Practical C++
  
  Learn how to write C++ code on your own computer and compile it into a executable program without running into too many compilation errors.
- Lesson 04: C++ Object Oriented Programming
  
  Learn the syntax of C++ object oriented programming as well as some of the additional OOP features provided by the language.
- Lesson 05: Python and C++ Speed
  
  In this lesson, we'll compare the execution times of C++ and Python programs.
Module 02: Performance Programming in C++
- Lesson 01: C++ Intro to Optimization
  
  Optimizing C++ involves understanding how a computer actually runs your programs. You'll learn how C++ uses the CPU and RAM to execute your code and get a sense for what can slow things down.
- Lesson 02: C++ Optimization Practice
  
  Now you understand how C++ programs execute. It's time to learn specific optimization techniques and put them into practice. This lesson will prepare you for the lesson's code optimization project.
- Lesson 03: Project: Optimize Histogram Filter
  
  Get ready to optimize some C++ code. You are provided with a working 2-dimensional histogram filter; your job is to get the histogram filter code to run faster!