Introduction to ml and dl
Download as PPTX, PDF0 likes77 views
The document provides an overview of neural networks, including their architecture, loss functions, and training processes such as forward and backward propagation. It includes practical coding examples and mentions applications of neural networks. Key terminologies and a simple example of model training are also discussed.
1 of 27
Download to read offline
![Let’s Code
.Sequential([ . .Dense =1 =[1])])
. ( sgd mean_squared_error )
x= np.array([0.0 ,3.0 ,5.0 ,6.0 ,8.0], dtype=float)
y= np.array([1.0 ,7.0, 11.0 ,13.0 ,17.0], dtype=float)
model.fit(x,y, epochs=500)](https://image.slidesharecdn.com/introductiontomlanddl-200619090533/85/Introduction-to-ml-and-dl-19-320.jpg)
More Related Content
What's hot (20)
PDF
Deep Learning for Computer Vision: Unsupervised Learning (UPC 2016)Universitat Politècnica de CatalunyaPDF
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)Universitat Politècnica de CatalunyaPPTX
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...Universitat Politècnica de CatalunyaPDF
Deep Learning for Computer Vision: Saliency Prediction (UPC 2016)Universitat Politècnica de CatalunyaPDF
The Perceptron (D1L1 Insight@DCU Machine Learning Workshop 2017)Universitat Politècnica de CatalunyaDeep Learning for Computer Vision: Unsupervised Learning (UPC 2016)Universitat Politècnica de Catalunya
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)Universitat Politècnica de Catalunya
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...Universitat Politècnica de Catalunya
Deep Learning for Computer Vision: Saliency Prediction (UPC 2016)Universitat Politècnica de Catalunya
The Perceptron (D1L1 Insight@DCU Machine Learning Workshop 2017)Universitat Politècnica de Catalunya
Similar to Introduction to ml and dl (20)
Ad
More from SuyashSingh70 (6)
Ad
Recently uploaded (20)
Introduction to ml and dl
- 4. What are Neural Networks?
- 5. What are Neural Networks?
- 6. Applications of Neural Networks:
- 14. The Loss Function (indicated in the graph by the dotted red line) (yellow dots)
- 15. Working Aim Can you see the pattern?
- 16. Neural Networks Source: Analytics Vidhya website
- 18. Ready for Code?
- 19. Let’s Code .Sequential([ . .Dense =1 =[1])]) . ( sgd mean_squared_error ) x= np.array([0.0 ,3.0 ,5.0 ,6.0 ,8.0], dtype=float) y= np.array([1.0 ,7.0, 11.0 ,13.0 ,17.0], dtype=float) model.fit(x,y, epochs=500)
- 21. Forward & Backward Propagation
- 22. Forward & Backward Propagation When training a network, we repeat the following steps (for n epoches): 1.Perform forward pass. 2.Calculate ∆W (the delta to be added to each weight) via backpropagation. 3.Update the weights.
- 23. Forward & Backward Propagation
- 24. Forward & Backward Propagation
- 25. Neural Networks
- 26. Neural Networks