Topic 05: Convolution Neural Networks
This chapter introduce –convolution neural networks (CNNs)– one of the most popular component of deep learning architecture. CNNs are widely applied in other domains such as natural language processing (NLP), audio, and time-series data. In this part, we introduce the CNNs, properties and component of CNN, differences between CNN and FCN as well as math behind the CNNs.
-
Chapter 05.01: Introduction of Convolution Neural Networks (CNNs)
In this part, we introduce the CNNs and when we can apply CNNs instead of FCN.
-
Chapter 05.02: Convolutional Operation
We learn about filters and convolution operation in this section.
-
Chapter 05.03: Properties of Convolution
We introduce three important properties by CNNs.
-
Chapter 05.04: CNN Components
We explain input channel, padding, stride, and pooling as CNN component.
-
Chapter 05.05: CNN Application
We overview some successful application of CNN in visual recognition.
-
Chapter 05.06: Convolutions- Mathematical Perspective
We explain the differences between convolution operation and cross-correlation.