Skip to content
Hallway
0:00 / 0:00

#cnn#convolutionalneuralnetwork#deeplearning

C4W1L10 CNN Example

DeepLearningAI

740K subscribers • 1 video on Hallway

YouTube
  • Recommended by 1 person: 1 on Stack Overflow and its sister sites.
  • May be out of date. Uploaded 8 years ago, in an area where tools change fast.

Intermediate. Assumes working knowledge.

141K views8 years ago1 recommendation

AI and machine learningNeural networks and deep learningComputer vision

An explanation of how convolutional neural networks process multi-channel images through successive layers of convolutions.

Take the Deep Learning Specialization: bit.ly/2TK8I7D Check out all our courses: deeplearning.ai Subscribe to The Batch, our weekly newsletter: deeplearning.ai/thebatch Follow us: Twitter: twitter.com/deeplearningai_ Facebook: facebook.com/deeplearningHQ/ Linkedin: linkedin.com/company/deeplearningai

Why it's here

1 person recommends this

What people say. Recommended for clarifying how multi-channel convolutions work in convolutional neural networks.

Sau001on Stack Overflow • Recommends

On “Number of feature maps produced after each convolution layer in CNN's”

I too had this confusion for a while and only after some digging did the mist clear away. Difference betweeen convolution with 1 channel and convolution with multiple channels This is where my understanding was going wrong. I will make an attempt to explain this difference. I am no expert so please bear with me Convolution operation with a single channel When we think of a simple gray scale 32X32 image and a convolution operation we are applying 1 or more convolution matrixes in the first layer. As per your example, each of these convolutional matrices of dimension 5X5 produces a 28x28 matrix as an output. Why 28X28? Because, you can slide a window of 5 pixels square in 32-5+1=28…
9View the answer