Difference between revisions of "Image Classification"
m |
m (Text replacement - "http:" to "https:") |
||
| Line 5: | Line 5: | ||
|description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools | |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools | ||
}} | }} | ||
| − | [ | + | [https://www.youtube.com/results?search_query=Image+Classification+deep+machine+learning+ML+artificial+intelligence+ai Youtube search...] |
| − | [ | + | [https://www.google.com/search?q=Image+Classification+deep+machine+learning+ML+artificial+intelligence+ai ...Google search] |
* [[...predict categories]] | * [[...predict categories]] | ||
| Line 21: | Line 21: | ||
* [[Image-to-Image Translation]] | * [[Image-to-Image Translation]] | ||
* [[ResNet-50]] | * [[ResNet-50]] | ||
| − | * [ | + | * [https://yann.lecun.com/exdb/mnist/ The MNIST Database | Y. LeCun, C. Cortes, and C. Burges] |
| Line 47: | Line 47: | ||
<youtube>0nqvO3AM2Vw</youtube> | <youtube>0nqvO3AM2Vw</youtube> | ||
<b>Lecture 2: Image Classification | <b>Lecture 2: Image Classification | ||
| − | </b><br>Lecture 2 introduces image classification as a core computer vision problem. We see that the image classification task is made challenging by the semantic gap, but that solutions to this task can be used as a building block in other more complicated computer vision systems. We introduce machine learning as a data-driven approach to solving hard problems like image classification. We discuss several common classification datasets in computer vision. Finally we introduce [[K-Nearest Neighbors (KNN)]] as our first machine learning algorithm. This leads to a discussion of hyperparameters and cross-validation strategies that will be crucial for all the machine learning algorithms we will later use. Slides: | + | </b><br>Lecture 2 introduces image classification as a core computer vision problem. We see that the image classification task is made challenging by the semantic gap, but that solutions to this task can be used as a building block in other more complicated computer vision systems. We introduce machine learning as a data-driven approach to solving hard problems like image classification. We discuss several common classification datasets in computer vision. Finally we introduce [[K-Nearest Neighbors (KNN)]] as our first machine learning algorithm. This leads to a discussion of hyperparameters and cross-validation strategies that will be crucial for all the machine learning algorithms we will later use. Slides: https://myumi.ch/ovgw7 |
|} | |} | ||
|<!-- M --> | |<!-- M --> | ||
| Line 77: | Line 77: | ||
= Microsoft Lobe = | = Microsoft Lobe = | ||
| − | * [ | + | * [https://lobe.ai/examples Lobe] aims to make it easy for anyone to train machine learning models. Free, private desktop application that has everything you need to take your machine learning ideas from prototype to production. This version of Lobe learns to look at images using image classification - categorizing an image into a single label overall. We are working to expand to more types of problems and data in future versions. |
{|<!-- T --> | {|<!-- T --> | ||
Revision as of 19:22, 27 March 2023
Youtube search... ...Google search
- ...predict categories
- Capabilities
- Case Studies
- Image Retrieval / Object Detection
- (Deep) Convolutional Neural Network (DCNN/CNN)
- Image/Video Transfer Learning
- Image-to-Image Translation
- ResNet-50
- The MNIST Database | Y. LeCun, C. Cortes, and C. Burges
|
|
|
|
|
|
Microsoft Lobe
- Lobe aims to make it easy for anyone to train machine learning models. Free, private desktop application that has everything you need to take your machine learning ideas from prototype to production. This version of Lobe learns to look at images using image classification - categorizing an image into a single label overall. We are working to expand to more types of problems and data in future versions.
|
|