322. Convolutional neural networks in two dimensions
Image classification on the MNIST and CIFAR-10 data sets
Building on the foundation we laid in Course 321 we extend our work on convolutional neural networks to two dimensions, working through a series of case studies.
You can enroll below for free or, if it's easier, unlock the entire End-to-End Machine Learning Course Catalog for 20 USD.
Course Curriculum
1. Classifying handwritten digits
Available in
days
days
after you enroll
-
Preview1.1 Welcome (2:23)
-
Preview1.2 Project overview (2:26)
-
Preview1.3 The MNIST digits data set (2:17)
-
Preview1.4 Overview of the convolutional neural network model (2:43)
-
Preview1.5 Results from pre-trained model (4:26)
-
Preview1.6 Examples of prediction successes and failures (6:02)
-
Preview1.7 Why Cottonwood? (3:05)
-
Preview1.8 Training code walkthrough: Setup (3:57)
-
Preview1.9 Training code walkthrough: Adding layers (3:13)
-
Preview1.10 Training code walkthrough: Connecting layers (3:33)
-
Preview1.11 Training code walkthrough: Training loop (3:06)
-
Preview1.12 Testing code walkthrough (5:10)
-
Preview1.13 Reporting code walkthrough: Loss history and text summary (4:42)
-
Preview1.14 Reporting code walkthrough: Collecting examples (5:44)
-
Preview1.15 Reporting code walkthrough: Rendering examples (6:08)
-
Preview1.16 Cottonwood tour: Core, experimental, data (5:27)
-
Preview1.17 Cottonwood tour: Tests, cheatsheet (3:47)
2. Convolution and a walking tour of the code
Available in
days
days
after you enroll
-
Preview2.1 How two dimensional convolution works
-
Preview2.2 Code tour: 2D convolution (introduction) (3:18)
-
Preview2.3 Code tour: 2D convolution initialization (8:36)
-
Preview2.4 Code tour: 2D convolution forward pass (10:52)
-
Preview2.5 Code tour: 2D convolution backward pass (7:21)
-
Preview2.6 Code tour: Bias layers (2:57)
3. Classifying CIFAR 10 images
Available in
days
days
after you enroll
-
Preview3.1 About the CIFAR 10 image classification data set (2:47)
-
Preview3.2 Get the data and the code (3:09)
-
Start3.3 Train, test, and evaluate the model (5:11)
-
Start3.4 Visualizing convolution layers and kernels (3:13)
-
Start3.5 Model structure and training curve (2:19)
-
Start3.6 Model creation and training (15:22)
-
Start3.7 Model testing (2:30)
-
Start3.8 Training curve (4:00)
-
Start3.9 Reporting script (5:00)
-
Start3.10 Reports (5:05)
-
Start3.11 Convolution reports (6:48)
-
Start3.12 Example images, correct and incorrectly classified (10:12)
-
Start3.13 Get the data into the model (8:36)
Get started now!
Frequently Asked Questions
When does the course start and finish?
The course starts now and never ends! It is a completely self-paced online course - you decide when you start and when you finish.
How long do I have access to the course?
How does lifetime access sound? After enrolling, you have unlimited access to this course for as long as you like - across any and all devices you own.
What if I am unhappy with the course?
We would never want you to be unhappy! If you are unsatisfied with your purchase, contact us in the first 30 days and we will give you a full refund.