You train a ConvNet on a dataset with cats, dogs, birds, and other types of animals. You try to find a filter that strongly responds to horizontal edges. You are more likely to find this filter in layer 6 of the network than in layer 1. True/False?
Question
You train a ConvNet on a dataset with cats, dogs, birds, and other types of animals. You try to find a filter that strongly responds to horizontal edges. You are more likely to find this filter in layer 6 of the network than in layer 1. True/False?
Solution
False. In a Convolutional Neural Network (ConvNet), the initial layers are more likely to detect simple and generic features like edges and textures. As we go deeper into the network, the layers tend to detect more complex and abstract features. Therefore, a filter that responds to horizontal edges is more likely to be found in the initial layers (like layer 1) rather than in the deeper layers (like layer 6).
Similar Questions
Question 6You train a ConvNet on a dataset with 100 different classes. You wonder if you can find a hidden unit which responds strongly to pictures of cats. (I.e., a neuron so that, of all the input/training images that strongly activate that neuron, the majority are cat pictures.) You are more likely to find this unit in layer 4 of the network than in layer 1.1 point
Which of the following statement is false? In Canny edge detection, non-maximum suppression is done along the direction of gradient but not along the direction of edge. DoG can be seen as a single non-separable 2D convolution or the difference of two separable convolutions. Canny edge detector is a linear filter because it uses the Gaussian filter to blur the image and then use linear filter to compute the gradient. DoG can be considered an approximation to the LoG.
Which is false?Group of answer choicesOutput of a layer in the residual network is the normal output (i.e, what’s produced after applying a filter and an activation function) + the layers input.Output of a layer in the dense network is the normal output (i.e, what’s produced after applying a filter and an activation function) + the layers input.Output of layer 𝑙 in the dense network will be one of the inputs for layers 𝑖∈(𝑙+1,𝐿) where 𝐿 is the total number of layers.A problem of convolution network is that some features may get extracted earlier in the network, but could be useful later on. However, it is hard to keep track of previous non-modified outputs.
Which statement is true?Group of answer choicesConvolutional neural networks tend to only have 10 layers.If the feature response value is large, then that portion of the image does not look like the filter.The convolutional kernel can only take all-positive or all-negative values at a time.If there is no pattern to find, the feature response is a weighted average with the result of blurring the image.
Which of the following do you typically see in ConvNet? (Check all that apply.)
Upgrade your grade with Knowee
Get personalized homework help. Review tough concepts in more detail, or go deeper into your topic by exploring other relevant questions.