Basics of Deep Learning
Download as PPTX, PDF0 likes141 views
The document provides an overview of deep learning, including: - An introduction to deep learning concepts like perceptrons, neural networks, forward and back propagation, and activation functions. - How deep learning can be applied to problems in computer vision, text processing, audio, and unstructured data. - The importance of regularization techniques like dropout and batch normalization to prevent overfitting in neural networks. - That deep learning requires large amounts of data and compute power to be effective.
Basics of Deep Learning
- 1. zekeLabs Basics of Deep Learning Learning made Simpler ! www.zekeLabs.com
- 2. Agenda ● Introduction to deep learning ● Understanding Perceptron ● Forward Propagation ● Activation Functions ● Building Neural Networks with Perceptrons ● Deep Neural Networks ● Applying Neural Network ● Training Neural Network ● Back Propagation ● Gradient Descent ● Overfitting
- 3. What is deep learning ?
- 4. Deep Learning Success ● Computer Vision ● Text Processing ● Audio ● Unstructured data ● In many places can replace humans
- 5. Why Now ?
- 6. When not to use Deep Learning ? ● More data is required for Deep Learning ● More Compute Power ● Models less interpretable “Don’t kill a mosquito with a cannon ball” Don’t use Deep Learning if you don’t need to
- 7. Perceptron Foundational Building Block of Deep Learning
- 9. Activation Functions The purpose of activation functions is to introduce non-linearities into the network
- 11. Purpose of Activation Functions The purpose of activation functions is to introduce non-linearities into the network
- 12. Building Neural Networks From Perceptrons
- 13. Representation
- 14. Representation - With Hidden Layer
- 16. Cost Function
- 17. Cost Function for Binary Classification
- 18. Cost Function for Regression
- 22. Overfitting Problems with complex models
- 23. Underfit - Perfectfit - Overfit
- 25. Regularization - Batch Normalization ● To increase the stability of a neural network, batch normalization normalizes the output of a previous activation layer by subtracting the batch mean and dividing by the batch standard deviation.
- 26. Regularization - Early Stopping
- 27. 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