Introduction to Machine Learning and Deep Learning with Spark and TensorFlow

Course Objectives

This “skills-centric” course is about 50% hands-on lab and 50% lecture, with extensive practical exercises designed to reinforce fundamental skills, concepts and best practices taught throughout the course.  Throughout the program, working in a hands-on learning environment guided by our expert instructor, students will

• Learn popular machine learning algorithms, their applicability, and limitations
• Practice the application of these methods in the Spark machine learning environment
• Learn practical use cases and limitations of algorithms
• Will explore not just the related APIs, but will also learn the theory behind them
• Work with real world datasets from Uber, Netflix, Walmart, Prosper, etc.

Need different skills or topics?  If your team requires different topics or tools, additional skills or custom approach, this course may be further adjusted to accommodate.  We offer additional big data, analytics. AI, machine learning, programming, Python/R and other related topics that may be blended with this course for a track that best suits your needs. Our team will collaborate with you to understand your needs and will target the course to focus on your specific learning objectives and goals.

Course Prerequisites

This is an intermediate level course, geared for Data Scientists, Data Analysts and Developers new to Machine Learning, Spark and TensorFlow.

Pre-Requisites:  Students should have attended or have incoming skills equivalent to those in this course:

• Strong basic Python Skills.  Attendees without Python background may view labs as follow along exercises or team with others to complete them.
• Good foundational mathematics in Linear Algebra and Probability
• Basic Linux skills, including familiarity with command-line options such as ls, cd, cp, and su

Please see the Related Courses tab for specific Pre-Requisite courses, Related Courses that offer similar skills or topics, and next-step Learning Path recommendations.

Course Agenda

Please note that this list of topics is based on our standard course offering, evolved from typical industry uses and trends. We will work with you to tune this course and level of coverage to target the skills you need most.

Part 1: Introduction to Machine Learning

1. Machine Learning (ML) Overview

• Machine Learning landscape
• Machine Learning applications
• Understanding ML algorithms & models

2. ML in Python and Spark

• Spark ML Overview
• Introduction to Jupyter notebooks
• Lab: Working with Jupyter + Python + Spark
• Lab: Spark ML utilities

3. Machine Learning Concepts

• Statistics Primer
• Covariance, Correlation, Covariance Matrix
• Errors, Residuals
• Overfitting / Underfitting
• Cross-validation, bootstrapping
• Confusion Matrix
• ROC curve, Area Under Curve (AUC)
• Lab: Basic stats

4. Feature Engineering (FE)

• Preparing data for ML
• Extracting features, enhancing data
• Data cleanup
• Visualizing Data
• Lab: data cleanup
• Lab: visualizing data

5. Linear regression

• Simple Linear Regression
• Multiple Linear Regression
• Running LR
• Evaluating LR model performance
• Lab
• Use case: House price estimates

6. Logistic Regression

• Understanding Logistic Regression
• Calculating Logistic Regression
• Evaluating model performance
• Lab: Use case: credit card application, college admissions

7. Classification: SVM (Supervised Vector Machines)

• SVM concepts and theory
• SVM with kernel
• Lab: Use case: Customer churn data

8. Classification: Decision Trees & Random Forests

• Theory behind trees
• Classification and Regression Trees (CART)
• Random Forest concepts
• Labs: Use case: predicting loan defaults, estimating election contributions

9. Classification: Naive Bayes

• Theory
• Lab
• Use case: spam filtering

10. Clustering (K-Means)

• Theory behind K-Means
• Running K-Means algorithm
• Estimating the performance
• Lab: Use case: grouping cars data, grouping shopping data

11. Principal Component Analysis (PCA)

• Understanding PCA concepts
• PCA applications
• Running a PCA algorithm
• Evaluating results
• Lab: Use case: analyzing retail shopping data

12. Recommendations (Collaborative filtering)

• Recommender systems overview
• Collaborative Filtering concepts
• Lab: Use case: movie recommendations, music recommendations

13. Performance 

• Best practices for scaling and optimizing Apache Spark
• Memory caching
• Testing and validation

Part Two: Introduction to Deep Learning with TensorFlow

14. Machine Learning Quick Review

• Understanding Machine Learning
• Supervised versus Unsupervised Learning
• Regression
• Classification
• Clustering

15. Introducing Tensorflow

• Tensorflow intro
• Tensorflow Features
• Tensorflow Versions
• GPU and TPU scalability
• Lab: Setting up and Running Tensorflow

16. The Tensor: The Basic Unit of Tensorflow

• Introducing Tensors
• Tensorflow Execution Model
• Lab: Learning about Tensors

17. Single Layer Linear Perceptron Classifier With TensorFlow

• Introducing Perceptrons
• Linear Separability and Xor Problem
• Activation Functions
• Softmax output
• Backpropagation, loss functions, and Gradient Descent
• Lab: Single-Layer Perceptron in Tensorflow

18. Hidden Layers: Intro to Deep Learning

• Hidden Layers as a solution to XOR problem
• Distributed Training with Tensorflow
• Vanishing Gradient Problem and ReLU
• Loss Functions
• Lab: Feedforward Neural Network Classifier in Tensorflow

19. High level Tensorflow: tf.learn

• Using high level tensorflow
• Developing a model with tf.learn
• Lab: Developing a tf.learn model

20. Convolutional Neural Networks in Tensorflow

• Introducing CNNs
• CNNs in Tensorflow
• Lab : CNN apps

21. Introducing Keras

• What is Keras?
• Using Keras with a Tensorflow Backend
• Lab: Example with a Keras

22. Recurrent Neural Networks in Tensorflow

• Introducing RNNs
• RNNs in Tensorflow
• Lab: RNN

23. Long Short-Term Memory (LSTM) in Tensorflow

• Introducing RNNs
• RNNs in Tensorflow
• Lab: RNN

24. Conclusion

• Summarize features and advantages of Tensorflow
• Summarize Deep Learning and How Tensorflow can help
• Next steps

Course Materials

Student Materials: Each participant will receive a Student Guide with course notes, code samples, software tutorials, step-by-step written lab instructions, diagrams and related reference materials and resource links. Students will also receive the project files (or code, if applicable) and solutions required for the hands-on work.

Hands-On Setup Made Simple! Our dedicated tech team will work with you to ensure our ‘easy-access’ cloud-based course environment is accessible, fully-tested and verified as ready to go well in advance of the course start date, ensuring a smooth start to class and effective learning experience for all participants. Please inquire for details and options.