Position Differences And Convolutional Neural Networks

Pete Warden shares his knowledge of how convolutional neural networks deal with position differences in images:

If you’re trying to recognize all images with the sun shape in them, how do you make sure that the model works even if the sun can be at any position in the image? It’s an interesting problem because there are really three stages of enlightenment in how you perceive it:

  • If you haven’t tried to program computers, it looks simple to solve because our eyes and brain have no problem dealing with the differences in positioning.

  • If you have tried to solve similar problems with traditional programming, your heart will probably sink because you’ll know both how hard dealing with input differences will be, and how tough it can be to explain to your clients why it’s so tricky.

  • As a certified Deep Learning Guru, you’ll sagely stroke your beard and smile, safe in the knowledge that your networks will take such trivial issues in their stride.

It’s a good read.

Related Posts

When Image Classifiers Look At Unknown Objects

Pete Warden explains that image classifiers aren’t magic: As people, we’re used to being able to classify anything we see in the world around us, and we naturally expect machines to have the same ability. Most models are only trained to recognize a very limited set of objects though, such as the 1,000 categories of the […]

Read More

Building Recurrent Neural Networks Using TensorFlow

Ahmet Taspinar walks us through creating a recurrent neural network topology using TensorFlow: As we have also seen in the previous blog posts, our Neural Network consists of a tf.Graph() and a tf.Session(). The tf.Graph() contains all of the computational steps required for the Neural Network, and the tf.Session is used to execute these steps. The computational steps defined in the tf.Graph can be […]

Read More

Categories

October 2017
MTWTFSS
« Sep Nov »
 1
2345678
9101112131415
16171819202122
23242526272829
3031