Lecture 5 | Convolutional Neural Networks
Why Artificial Intelligence Stack Exchange recommends it
Artificial Intelligence Stack Exchange users cite it as a reference for how convolutional layers work and how CNNs differ from ordinary neural networks.
Recommended by 1 people across 1 different months, 2017 to 2021.
What it is
Lecture 5 of Stanford's CS231n (2017) moves from fully-connected networks to convolutional neural networks. It covers historical milestones (perceptron, neocognitron, LeNet, AlexNet) and introduces convolution, pooling and fully-connected layers. Taught by the course's Stanford instructors (Fei-Fei Li, Justin Johnson, Serena Yeung).
What people said
Recommends Demento · 2017-11 · Artificial Intelligence Stack Exchange · on “What is the difference between pixel-based object recognition and feature-based object recognition?”
Pixel based object recognition , like the name says, works by analyzing the individual pixels of an image. For example: You analyze an image with a lot of different shades of blue and some grey pixels - you might assume that this is the picture of a plane in the sky or a ship in the water. You could also look for similar pictures by calculating the difference between each individual pixel of 2 images and sum up the differences. The smaller the sum of the difference, the more the pictures look alike. It depends on your field of work, but those methods will most likely not be good enough for solid image recognition. You also mentioned neural networks. Of course you can feed the raw pixel data
Cites Jackson Waschura · 2018-03 · Artificial Intelligence Stack Exchange · on “What is the difference between a convolutional neural network and a regular neural network?”
Convolutional Neural Networks (CNNs) are neural networks with architectural constraints to reduce computational complexity and ensure translational invariance (the network interprets input patterns the same regardless of translation— in terms of image recognition: a banana is a banana regardless of where it is in the image). Convolutional Neural Networks have three important architectural features. Local Connectivity: Neurons in one layer are only connected to neurons in the next layer that are spatially close to them. This design trims the vast majority of connections between consecutive layers, but keeps the ones that carry the most useful information. The assumption made here is that the
Cites Rocky the Owl · 2021-09 · Artificial Intelligence Stack Exchange · on “How do convolutional layers of basic Graph Convolutional Networks work?”
I was reading the following article on Towards Data Science ( here [LINK] ) and it says the following, regarding the calculation of convolutional layers: So the overall steps are: Transform the graph into the spectral domain using eigendecomposition Apply eigendecomposition to the specified kernel Multiply the spectral graph and spectral kernel (like vanilla convolutions) Return results in the original spatial domain (analogous to inverse GFT) Question: How can we visualize the convolutional layer working for a graph neural network? For example, for a CNN we can imagine the following (source: Stanford CS231n YouTube lectures, Lecture 5: Convolutional Neural Networks ( here [this video] )). What i