Status Quo?
2. Inner Working of a NN
2.1 Forward Propagation
Neuron
Layers
Weights
Activation & Weights
Activation & Weights
Sigmoid
Bias
Learning
Matrix operations
Matrix operations
Neuron is a function
NN is a function
Sigmoid VS ReLU
2.2 Gradient Descent
Cost Function
High Cost
Low Cost
Average Cost
NN Function Parameters
Cost Function Parameters
1D Cost Function
2D Cost Function
Gradient Descent
Find the shortest path to walk down a hill
One step after another...
2.3 Back Propagation
Different importance of components
Propagating Backward
Summary - Looking back at 'our three figures'
Forward Propagation
Gradient Descent
back Propagation
Machine Learning Project Checklist
- 1. Frame the problem and look at the big picture.
- 2. Get the data.
- 3. Explore the data to gain insights.
- 4. Prepare the data to better expose the underlying data patterns to Machine Learning algorithms.
- 5. Explore many different models and short-list the best ones.
- 6. Fine-tune your models and combine them into a great solution.
- 7. Present your solution.
- 8. Launch, monitor, and maintain your system.
Credits
- Photos unsplash.com
- Diagrams 3Blue1Brown
- Checklist Hands-On Machine Learning with Scikit-Learn and TensorFlow