1 / 25

Convolutional Networks

Convolutional Networks. Extracted from NN for ML Coursera by Prof. Hinton. Weight sharing to detect the same features at different locations in the image Reduces number of free parameters (only 9 different weights here) Brings us some translation invariance

louise
Download Presentation

Convolutional Networks

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Convolutional Networks Extracted from NN for ML Coursera by Prof. Hinton

  2. Weight sharing to detect the same features at different locations in the image • Reduces number of free parameters (only 9 different weights here) • Brings us some translation invariance • We want multiple feature maps, each of which shares weights within itself

  3. Hinton’s Note on Proper Concept of Invariance

  4. Le Net by Yann LeCun

  5. CNN for Object Recognition

  6. Rectified Linear Units A smooth approximate to the rectifieris the softplusfunction. f(x) = log (1 + ex) The derivative of softplus is , i.e. the logistic function. • f(x) = max(0,x) • Gradient is defined as 0 if x < 0 1 if x > 0 ON RECTIFIED LINEAR UNITS FOR SPEECH PROCESSING, Zeiler, … Hinton et al

  7. The advantages of using Rectified Linear Units in neural networks are: • It  induces the sparsity in the hidden units. • ReLU doesn't face gradient vanishing problem as faced by sigmoid and tanh function. It has been shown that deep networks can be trained efficiently using ReLU even without pre-training. • ReLU can be used in Restricted Boltzmann machine to model real/integer valued inputs.

More Related