Skip to main content

Course - Art and Science of ML

Introduction​

Course overview highlighting the key objectives and modules. First, you will learn about aspects of Machine Learning that require some intuition, good judgment and experimentation. We call it the Art of ML. You will learn the many knobs and levers involved in training a model. You will manually adjust them to see their effects on model performance.

The Art of ML​

In this course you will learn about The Art of Machine Learning. We will review aspects of machine learning that require intuition, judgment and experimentation to find the right balance and what's good enough (spoiler alert: it's never perfect!).

  • Video:Introduction
  • Video:Regularization
  • Video:L1 & L2 Regularizations - What is L1 and L2 regularization? What are the differences between the two?
  • Video:Lab Intro: Regularization
  • Video:Lab: Regularization
  • Video:Learning rate and batch size
  • Video:Optimization
  • Video:Practicing with Tensorflow code
  • Video:Lab Intro: Hand-Tuning ML Models
  • Video:Lab Solution: Hand-Tuning ML Models
  • Graded:Art of ML
  • Graded:Hand-Tuning ML Models
  • Graded:Learning Rate and Batch Size

Hyperparameter Tuning​

In this module you will learn how to differentiate between parameters and hyperparameters. Then we'll discuss traditional grid search approach and learn how to think beyond it with smarter algorithms. Finally you'll learn how Cloud ML engine makes it so convenient to automate hyperparameter tuning.

  • Video:Introduction
  • Video:Parameters vs Hyperparameters
  • Video:Think Beyond Grid Search
  • Video:Lab Intro: Improve model accuracy by Hyperparameter Tuning with Cloud MLE
  • Video:Lab Solution: Improve model accuracy by Hyperparameter Tuning with Cloud MLE
  • Graded:Improve model accuracy by Hyperparameter Tuning with Cloud MLE
  • Graded:Hyperparameter Tuning

A pinch of science​

In this module, we will start to introduce the science along with the art of machine learning. We're first going to talk about how to perform regularization for sparsity so that we can have simpler, more concise models. Then we're going to talk about logistic regression and learning how to determine performance.

  • Video:Introduction
  • Video:Regularization for sparsity
  • Video:Lab: L1 Regularization
  • Video:Lab Solution: L1 Regularization
  • Video:Logistic Regression
  • Graded:L1 Regularization
  • Graded:Logistic Regression

The science of neural networks​

In this module we will now be diving deep into the science, specifically with neural networks.

  • Video:Introduction
  • Video:Neural Networks
  • Video:Lab: Neural Networks Playground
  • Video:Training Neural Networks
  • Video:Lab: Using Neural Networks to build a ML model
  • Video:Multi-class Neural Networks
  • Graded:Using Neural Networks to Build a ML Model
  • Graded:Training Neural Networks
  • Graded:Multi-class Neural Networks

Custom Estimator​

In this module we will go beyond using canned estimators by writing a custom estimator. By writing a custom estimator, you will be able to gain greater control over the model function itself.

  • Video:Custom Estimator
  • Video:Model Function
  • Video:Lab: Implementing a Custom Estimator
  • Video:Keras Models
  • Video:Demo: Keras Models + Estimator
  • Graded:Implementing a Custom Estimator
  • Graded:Custom Estimator