Deep Learning A-Z™: Artificial Neural Networks (ANN) - Stochastic Gradient Descent
2 likes1,729 views
The document discusses gradient descent and updating weights (w's) in a neural network. It provides mathematical formulas for cost (C) as the sum of squared errors between predicted (y^) and true (y) values. It describes adjusting the weights w1, w2, w3 to minimize cost via gradient descent. References are provided for additional reading on implementing neural networks in Python and the fundamentals of neural networks and deep learning.
Related topics:1 of 8
Deep Learning A-Z™: Artificial Neural Networks (ANN) - Stochastic Gradient Descent
- 2. © SuperDataScienceDeep Learning A-Z C = ½(ŷ- y)2 C ŷ
- 3. © SuperDataScienceDeep Learning A-Z C ŷ Best!
- 4. © SuperDataScienceDeep Learning A-Z C = ∑ ½(ŷ- y)2 X1 X2 Xm w1 w2 wm ŷ y X1 X2 Xm w1 w2 wm ŷ y X1 X2 Xm w1 w2 wm ŷ y X1 X2 Xm w1 w2 wm ŷ y X1 X2 Xm w1 w2 wm ŷ y X1 X2 Xm w1 w2 wm ŷ y X1 X2 Xm w1 w2 wm ŷ y X1 X2 Xm w1 w2 wm ŷ y ŷ y C ŷ y ŷ y ŷ y ŷ y ŷ y ŷ y ŷ y Adjust w1, w2, w3
- 5. © SuperDataScienceDeep Learning A-Z C = ∑ ½(ŷ- y)2 X1 X2 Xm w1 w2 wm ŷ y X1 X2 Xm w1 w2 wm ŷ y X1 X2 Xm w1 w2 wm ŷ y X1 X2 Xm w1 w2 wm ŷ y X1 X2 Xm w1 w2 wm ŷ y X1 X2 Xm w1 w2 wm ŷ y X1 X2 Xm w1 w2 wm ŷ y X1 X2 Xm w1 w2 wm ŷ y ŷ y C ŷ y ŷ y ŷ y ŷ y ŷ y ŷ y ŷ y Adjust w1, w2, w3Adjust w1, w2, w3Adjust w1, w2, w3
- 6. © SuperDataScienceDeep Learning A-Z Upd w’s Upd w’s Upd w’s Upd w’s Upd w’s Upd w’s Upd w’s Upd w’s Upd w’s
- 7. © SuperDataScienceDeep Learning A-Z A Neural Network in 13 lines of Python (Part 2 - Gradient Descent) Andrew Trask (2015) Link: https://iamtrask.github.io/2015/07/27/python-network-part2/ Additional Reading:
- 8. © SuperDataScienceDeep Learning A-Z Neural Networks and Deep Learning Michael Nielsen (2015) Link: http://neuralnetworksanddeeplearning.com/chap2.html Additional Reading: