Course
Digicomp Code MLGCP5
Art and Science of Machine Learning («MLGCP5»)
Welcome to the Art and Science of Machine Learning. The course covers the essential skills of ML intuition, good judgment and experimentation needed to finely tune and optimize ML models for the best performance.
Duration
1 day
Price
850.–
Course documents
Official Google Cloud courseware
Course facts
- Generalizing a ML model using Regularization techniques
- Tuning batch size and learning rate for better model performance
- Optimizing a ML model
- Applying the concepts in TensorFlow code
- Course overview and scope
- Introduction to Google Cloud and Qwiklabs
- Generalization
- Optimization
- Generalize your model
- Tune batch size and learning rate for better model performance
- Optimize your model
- Apply the concepts in TensorFlow code
- Hyperparameter tuning
- Learning Rate
- Batch size
- Differentiate between parameters and hyperparameters
- Think beyond simple grid search algorithms
- Use Cloud AI Platform for hyperparameter tuning
- L1 Regularization
- L2 Regularization
- Apply L1 and L2 regularization for sparsity
- Understand why regularization is important for Logistic Regression
- Neural networks
- Multi-class neural networks
- Train Neural Networks effectively
- Work with multi-class Neural Networks
- Course overview
- Summarize course
- Aspiring machine learning data scientists and engineers
- Machine learning scientists, data scientists, and data analysts
- Data engineers
- Some familiarity with basic machine learning concepts
- Basic proficiency with a scripting language (Python preferred)