Advanced Learning Algorithms by Coursera
Course Highlights
- Build and train a neural network with TensorFlow to perform multi-class classification.
- Apply best practices for machine learning development so that your models generalize to data and tasks in the real world.
- Build and use decision trees and tree ensemble methods, including random forests and boosted trees.
Skills you will learn!
Curriculum
26 Topics
Welcome!
Neurons and the brain
Demand Prediction
Example: Recognizing Images
Neural network layer
More complex neural networks
Inference: making predictions (forward propagation)
Inference in Code
Data in TensorFlow
Building a neural network
Forward prop in a single layer
General implementation of forward propagation
Is there a path to AGI?
How neural networks are implemented efficiently
Matrix multiplication
Matrix multiplication rules
Matrix multiplication code
[IMPORTANT] Have questions issues or ideas? Join our Forum!
Practice quiz: Neural networks intuition
Practice quiz: Neural network model
Practice quiz: TensorFlow implementation
Practice quiz: Neural network implementation in Python
Practice Lab: Neural Networks for Binary Classification
Neurons and Layers
Coffee Roasting in Tensorflow
CoffeeRoastingNumPy
25 Topics
TensorFlow implementation
Training Details
Alternatives to the sigmoid activation
Choosing activation functions
Why do we need activation functions?
Multiclass
Softmax
Neural Network with Softmax output
Improved implementation of softmax
Classification with multiple outputs (Optional)
Advanced Optimization
Additional Layer Types
What is a derivative? (Optional)
Computation graph (Optional)
Larger neural network example (Optional)
Practice quiz: Neural Network Training
Practice quiz: Activation Functions
Practice quiz: Multiclass Classification
Practice quiz: Additional Neural Network Concepts
Practice Lab: Neural Networks for Multiclass classification
ReLU activation
Softmax
Multiclass
Optional Lab: Derivatives
Optional Lab: Back propagation
23 Topics
Deciding what to try next
Evaluating a model
Model selection and training/cross validation/test sets
Diagnosing bias and variance
Regularization and bias/variance
Establishing a baseline level of performance
Learning curves
Deciding what to try next revisited
Bias/variance and neural networks
Iterative loop of ML development
Error analysis
Adding data
Transfer learning: using data from a different task
Full cycle of a machine learning project
Fairness bias and ethics
Error metrics for skewed datasets
Trading off precision and recall
Practice quiz: Advice for applying machine learning
Practice quiz: Bias and variance
Practice quiz: Machine learning development process
Practice Lab: Advice for Applying Machine Learning
Optional Lab: Model Evaluation and Selection
Optional Lab: Diagnosing Bias and Variance
22 Topics
Decision tree model
Learning Process
Measuring purity
Choosing a split: Information Gain
Putting it together
Using one-hot encoding of categorical features
Continuous valued features
Regression Trees (optional)
Using multiple decision trees
Sampling with replacement
Random forest algorithm
XGBoost
When to use decision trees
Andrew Ng and Chris Manning on Natural Language Processing
[IMPORTANT] Reminder about end of access to Lab Notebooks
Acknowledgements
Practice quiz: Decision trees
Practice quiz: Decision tree learning
Practice quiz: Tree ensembles
Practice Lab: Decision Trees
Optional Lab: Decision Trees
Optional Lab: Tree Ensembles
Advanced Learning Algorithms
Related Deep Learning Courses
Thank You!
Your review has been submitted successfully.