Course Overview

Algorithms of the Intelligent Web is a hands-on Applied Machine Learning & AI course that teaches you how to create machine learning applications that crunch and wrangle data collected from users, web applications and website logs. Leveraging the most current standards, skills, and practices, you’ll examine intelligent algorithms that extract real value from data. Key machine learning concepts are explained with code examples in Python’s scikit-learn. This course guides you through algorithms to capture, store, and structure data streams coming from the web. You’ll explore recommendation engines and dive into classification via statistical algorithms, neural networks, and deep learning.

Key Learning Areas

Our engaging instructors and mentors are highly experienced practitioners who bring years of current, modern "on-the-job" modern applied Data Science, AI and Machine Learning experience into every classroom and hands-on project. Working in a hands-on lab environment led by our expert instructor, attendees will explore

  • Machine learning essentials, as well as deep learning and neural networks
  • How recommendation engines work
  • Building applications for the intelligent web
  • Extracting structure from data: clustering and transforming your data
  • Recommending relevant content
  • Classification: placing things where they belong
  • Relevant Case Study: click prediction for online advertising
  • Making the right Machine Learning choices for your web apps
  • The future of the intelligent web

Course Outline

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.

Building Applications for the Intelligent Web

  • An intelligent algorithm in action: Google Now
  • The intelligent-algorithm lifecycle
  • Further examples of intelligent algorithms
  • Things that intelligent applications are not
  • Classes of intelligent algorithm
  • Evaluating the performance of intelligent algorithms
  • Important notes about intelligent algorithms

Extracting Structure from Data: Clustering and Transforming your Data

  • Data, structure, bias, and noise
  • The curse of dimensionality
  • K-means
  • The relationship between k-means and GMM
  • Transforming the data axis

Recommending Relevant Content

  • Setting the scene: an online movie store
  • Distance and similarity
  • How do recommendation engines work?
  • User-based collaborative filtering
  • Model-based recommendation using singular value decomposition
  • The Netflix Prize
  • Evaluating your recommender

Classification: Placing Things Where They Belong

  • The need for classification
  • An overview of classifiers
  • Algorithms
  • Fraud detection with logistic regression
  • Are your results credible?
  • Classification with very large datasets

Case Study: Click Prediction for Online Advertising

  • History and background
  • The exchange
  • What is a bidder?
  • What is a decisioning engine?
  • Click prediction with Vowpal Wabbit
  • Complexities of building a decisioning engine
  • The future of real-time prediction

Deep Learning and Neural Networks

  • An intuitive approach to deep learning
  • Neural networks
  • The perceptron
  • Multilayer perceptrons
  • backpropagation
  • Going deeper: from multilayer neural networks to deep learning

Making the Right Choice

  • A/B testing
  • Multi-armed bandits
  • Bayesian bandits in the wild
  • A/B vs. the Bayesian bandit
  • Extensions to multi-armed bandits

The Future of the Intelligent Web

  • Future applications of the intelligent web
  • Social implications of the intelligent web

Who Benefits

This course is geared for attendees with who wish to capture, store, and structure data streams coming from the web. You’ll explore recommendation engines and dive into classification via statistical algorithms, neural networks, and deep learning.

Prerequisites

  • Basic to Intermediate IT Skills, with some prior Python exposure if able. Attendees without a programming background like Python may view labs as follow along exercises or team with others to complete them.
  • Good foundational mathematics or logic skills
  • Basic Linux skills, including familiarity with command-line options such as ls, cd, cp, and su