9 – 10 Visualizing Activations V1 RENDER V2

For intermediate layers, like the second convolutional layer in a CNN, visualizing the learned weights in each filter doesn’t give us easy to read information. So, how can we visualize what these deeper layers are seeing? Well, what can give us useful Information is to look at the feature maps of these layers as the … Read more

8 – 06 First Convolutional Layer T1 V1 RENDER V2

The first convolutional layer in a CNN applies a set of image filters to an input image and outputs a stack of feature maps. After such a network is trained, we can get a sense of what kinds of features this first layer has learned to extract by visualizing the learned weights for each of … Read more

7 – 05 Feature Maps V1RENDER V3

Let’s start near the beginning of this CNN. We’ve talked about how the first convolutional layer in a CNN consists of a number of filtered images that are produced as the input image is convolved with a set of image filters. These filters are just grids of weights. For a convolutional layer with four filters, … Read more

6 – 04 Feature Visualization V1 RENDER V2

Let’s look at the architecture of a classification CNN that takes in an image and outputs a predicted class for that image. You’ve seen how to train CNN’s like this on sets of labeled image data, and you’ve learned about the layers that make up a CNN. Things like convolutional layers that learned to filter … Read more

5 – 动量

So, here’s another way to solve a local minimum problem. The idea is to walk a bit fast with momentum and determination in a way that if you get stuck in a local minimum, you can, sort of, power through and get over the hump to look for a lower minimum. So let’s look at … Read more

4 – Dropout

Here’s another way to prevent overfitting. So, let’s say this is you, and one day you decide to practice sports. So, on Monday you play tennis, on Tuesday you lift weights, on Wednesday you play American football, on Thursday you play baseball, on Friday you play basketball, and on Saturday you play ping pong. Now, … Read more

3 – Pooling Layers

We’re now ready to introduce you to the second and final type of layer that we’ll need to introduce before building our own convolutional neural networks. These so-called pooling layers often take convolutional layers as input. Recall that a convolutional layer is a stack of feature maps- where we have one feature map for each … Read more

2 – Convolutional Layers (Part 2)

Consider this image of a dog. A single region in this image may have many different patterns that we want to detect. Consider this region for instance. This region has teeth, some whiskers, and a tongue. In that case, to understand this image, we need filters for detecting all three of these characteristics, one for … Read more

10 – 20 Summary Of Feature Viz V2 RENDER V2

Several approaches for understanding and visualizing convolutional networks have been developed in the literature. Partly, as a response to the common criticism that the learned features in a neural network are not interpretable. Now, you’ve seen a view of the most commonly used feature visualization techniques from looking at filter weights to looking at layer … Read more

1 – 03 Data And Lesson Outline RENDER V2

In this lesson, to learn about CNNs, we’ll first talk about the layers that make up an image classification CNN. You’ll learn how to define these layers, and what role each plays in extracting information from an input image. After learning about these layers, you’ll see how to define a CNN that aims to classify … Read more