Note: All images in this directory, unless specified otherwise, are licensed under CC BY-NC 4.0.
| Figure number | Description | Notes |
|---|---|---|
| 3-1 | Transfer learning in real life | |
| 3-2 | A high-level overview of a CNN | |
| 3-3 | (a) Lower-level activations, followed by (b) midlevel activations and (c) upper-layer activations | Pages 5 and 7 in Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations |
| 3-4 | An overview of transfer learning | |
| 3-5 | Fine tuning a convolutional neural network | |
| 3-6 | Example directory structure of the training and validation data for different classes | |
| 3-7 | Underfitting, overfitting, and ideal fitting for points close to a sine curve | |
| 3-8 | Possible image augmentations generated from a single image | |
| 3-9 | Images with the highest probability of containing dogs | |
| 3-10 | Images with the lowest probability of containing dogs | |
| 3-11 | Images of cats with the highest probability of containing dogs | |
| 3-12 | Images with the highest probability of containing cats | |
| 3-13 | Images with the lowest probability of containing cats | |
| 3-14 | Images of dogs with the highest probability of containing cats | |
| 3-15 | Building a neural network in TensorFlow Playground | |
| 3-16 | Defining a CNN and visualizing the output of each layer during training in ConvNetJS |
