Lesson List
3.01 Neural Networks (RNNs, CNNs & GANs)
We will cover the differences between RNN's and CNN's. In this class, we will demonstrate some of the basic RNN models such as LSTM's, lookback and attention models, and we will learn about various ways that CNN's are used to classify and identify objects, and we will touch upon the relatively new concept of GANs or Generative Adversarial Networks. We will also learn why it is important to make AI training as efficient as possible, in all forms of neural network.
0/3
4.01 AI Science Fair Projects & Real World Applications
In this class, we will discuss and show some real world examples of of AI, as well as some top science fair projects using AI, and we will walk through the technologies behind them.
2.01 Face Detection vs Face Recognition
In this section, we will discuss what it takes to make computers learn and understand things. We will cover topics such as data, training and testing. We will also cover some of basic AI terms and concepts like weights, biases, algorithms, generative AI vs AI for predictions/classifications, basic AI visualizations, and some of the ways that these concepts are applied in the real world.
1.01 Basics of AI
We will cover the history of computers and AI, and why we are where we are today. We will discuss the background of AI/machine learning theories, some common definitions and misconceptions, and learn about the evolution of AI over time. We will also discuss why today's computer chips, as well as big data and algorithms are capable of making AI possible, and where AI is headed in the near future.
0/2
This feature has been disabled by the administrator
Lesson: Face Detection
Overview
Exercise Files
About Lesson
File:Jimmy_answering_questions.jpg licensed with Cc-by-2.0, Cc-by-3.0 2009-09-01T21:13:02Z Flickr upload bot 3888×2600 (3777031 Bytes) Uploaded from http://flickr.com/photo/41749772@N06/3857644058 using [[User:Flickr upload bot|Flickr upload bot]] This file is licensed under the Creative Commons Attribution 3.0 Unported license. This file is licensed under the Creative Commons Attribution 3.0 Unported license.

Face detection has been around for quite some time.  Decades, in fact.  It’s in all of our phones, and it is the basis of many AI techniques, including deepfakes.  It is in our very human nature, to look for other people, and recognize them by face.  So, one of the first technologies developed in AI was the ability to find faces, both in images and in videos.  

Face detection programs are different from face recognition in 

Exercise Files
No Attachment Found
No Attachment Found
Lesson List
3.01 Neural Networks (RNNs, CNNs & GANs)
We will cover the differences between RNN's and CNN's. In this class, we will demonstrate some of the basic RNN models such as LSTM's, lookback and attention models, and we will learn about various ways that CNN's are used to classify and identify objects, and we will touch upon the relatively new concept of GANs or Generative Adversarial Networks. We will also learn why it is important to make AI training as efficient as possible, in all forms of neural network.
0/3
4.01 AI Science Fair Projects & Real World Applications
In this class, we will discuss and show some real world examples of of AI, as well as some top science fair projects using AI, and we will walk through the technologies behind them.
2.01 Face Detection vs Face Recognition
In this section, we will discuss what it takes to make computers learn and understand things. We will cover topics such as data, training and testing. We will also cover some of basic AI terms and concepts like weights, biases, algorithms, generative AI vs AI for predictions/classifications, basic AI visualizations, and some of the ways that these concepts are applied in the real world.
1.01 Basics of AI
We will cover the history of computers and AI, and why we are where we are today. We will discuss the background of AI/machine learning theories, some common definitions and misconceptions, and learn about the evolution of AI over time. We will also discuss why today's computer chips, as well as big data and algorithms are capable of making AI possible, and where AI is headed in the near future.
0/2
This feature has been disabled by the administrator
0% Complete