Convolutional Neural Network
Download as PPTX, PDF0 likes118 views
This document provides an agenda for a convolutional neural network training presentation. The presentation covers concepts like filters, strides, padding, pooling, fully connected layers, and overfitting. It aims to simplify machine learning and help attendees understand how convolutional neural networks work. Contact information is provided at the end for anyone interested in the company's training services.
Convolutional Neural Network
- 1. zekeLabs Convolutional Neural Network Learning made Simpler ! www.zekeLabs.com
- 2. Agenda ●
- 3. Filters
- 4. Filters
- 5. Filters
- 6. Strides
- 7. Output dim after Conv
- 8. Padding
- 10. Pooling
- 11. Max Pooling
- 12. Fully Connected Layer ● High Level Features maps to a particular class ● A FC layer looks at what high level features most strongly correlate to a particular class and has particular weights so that when you compute the products between the weights and the previous layer, you get the correct probabilities for the different classes.
- 13. Overfitting Problems with complex models
- 14. Visit : www.zekeLabs.com for more details THANK YOU Let us know how can we help your organization to Upskill the employees to stay updated in the ever-evolving IT Industry. Get in touch: www.zekeLabs.com | +91-8095465880 | info@zekeLabs.com