Buy Now AED 344.99 + VAT

Monthly Subscription Starting at AED 99 + VAT

Introduction to Applied Machine Learning
  • Level Professional
  • المدة 7 ساعات hours
  • الطبع بواسطة Alberta Machine Intelligence Institute
  • Offered by

عن

This course is for professionals who have heard the buzz around machine learning and want to apply machine learning to data analysis and automation. Whether finance, medicine, engineering, business or other domains, this course will introduce you to problem definition and data preparation in a machine learning project. By the end of the course, you will be able to clearly define a machine learning problem using two approaches. You will learn to survey available data resources and identify potential ML applications. You will learn to take a business need and turn it into a machine learning application. You will prepare data for effective machine learning applications. This is the first course of the Applied Machine Learning Specialization brought to you by Coursera and the Alberta Machine Intelligence Institute.

الوحدات

Lesson 1: Definitions

    • 6 Videos
    • 2 Readings
    • 3 Discussion
    • 1 Assignment
Show info about module content

1 Assignment

  • Concepts and Definitions

3 Discussions

  • Artificial Intelligence Viewpoints
  • Meet and Greet!
  • Misunderstandings surrounding AI and ML

6 Videos

  • Introduction to the Applied Machine Learning Specialization
  • Instructor Introduction
  • Introduction to Course 1
  • What is Artificial Intelligence and Machine Learning?
  • What about Data Science?
  • The Machine Learning Process

2 Readings

  • What about Deep Learning? (supplemental)
  • Fooling Neural Networks (supplemental)

Lesson 2: Supervised Learning

    • 3 Videos
    • 3 Readings
Show info about module content

3 Videos

  • The Three Kinds of Machine Learning
  • Classification: What is it and how does it work?
  • Regression: Fitting lines and predicting numbers

3 Readings

  • How to Curate A Ground Truth For Your Business Dataset (Required)
  • Learning From Multiple Annotators: A Survey (supplemental)
  • Inferring the Ground Truth Through Crowdsourcing (supplemental)

Lesson 3: Broader Machine Learning

    • 3 Videos
    • 1 Readings
    • 1 Assignment
Show info about module content

1 Assignment

  • Identifying Machine Learning Techniques

3 Videos

  • Unsupervised Learning
  • Reinforcement Learning
  • Weekly Summary

1 Readings

  • Semi Supervised Learning (required)

Lesson 1: Machines are Different From Humans

    • 2 Videos
    • 1 Discussion
Show info about module content

1 Discussions

  • Explainability and Accuracy for a QuAM

2 Videos

  • Generalization and how machines actually learn
  • Features and transformations of raw data

Lesson 2: Applied Scenarios

    • 2 Videos
    • 3 Readings
Show info about module content

2 Videos

  • Farmer Betty and Her Precision Agriculture Plans
  • What to consider when using your QuAM

3 Readings

  • A Brief Introduction into Precision Agriculture
  • Farmer Betty Tried Unsupervised Learning (required)
  • Data is Central to Your ML Problem (required)

Lesson 3: Getting Good Questions

    • 4 Videos
    • 1 Readings
    • 1 Discussion
    • 1 Assignment
Show info about module content

1 Assignment

  • Machine Learning in the Real World Review

1 Discussions

  • All About Proxies

4 Videos

  • Broad Examples Narrowed Down
  • Identify Business Evaluation
  • Everything is a Proxy
  • Weekly Summary

1 Readings

  • Martin Zinkevich's Rules for ML (supplemental)

Lesson 1: Data Needs

    • 2 Videos
    • 1 Discussion
Show info about module content

1 Discussions

  • Sources of Data

2 Videos

  • Sources of Training Data
  • How Much Data Do I Need?

Lesson 2: Data Relates to Problems

    • 3 Videos
    • 2 Readings
    • 1 Discussion
Show info about module content

1 Discussions

  • Bias and Noise

3 Videos

  • Ethical Issues
  • Bias in Data Sources
  • Noise and Sources of Randomness

2 Readings

  • Data Protection Laws (required)
  • Government readings on data privacy (supplemental)

Lesson 3: Data Process

    • 4 Videos
    • 1 Assignment
Show info about module content

1 Assignment

  • Understanding Data for ML

4 Videos

  • Image Classification Example
  • Data Cleaning: Everybody's favourite task
  • Why you need to set up a Data Pipeline
  • Weekly Summary

Lesson 1: Machine Learning Process Lifecycle

    • 2 Videos
    • 1 Readings
Show info about module content

2 Videos

  • MLPL Overview
  • MLPL as experienced by Farmer Betty

1 Readings

  • Machine Learning Process Lifecycle Explained

Lesson 2: Getting Ready to Model

    • 2 Videos
    • 1 Discussion
Show info about module content

1 Discussions

  • What task can machine learning help you with?

2 Videos

  • Exploring the process of problem definition
  • Assessing your QuAM for use in your Business

Lesson 3: Model Learning and Evaluation

    • 3 Videos
    • 1 Readings
    • 1 Discussion
    • 1 Assignment
Show info about module content

1 Assignment

  • Understanding Machine Learning Projects

1 Discussions

  • False Positives and False Negatives

3 Videos

  • Technically Assessing the Strength of your QuAM
  • Different Kinds of Wrong
  • Weekly Summary

1 Readings

  • Deep Learning for Identifying Metastatic Breast Cancer (advanced supplemental)

Auto Summary

Dive into "Introduction to Applied Machine Learning," a comprehensive course tailored for professionals eager to leverage machine learning for data analysis and automation across various fields like finance, medicine, engineering, and business. Guided by experts from the Alberta Machine Intelligence Institute and Coursera, you'll master problem definition, data preparation, and the transformation of business needs into ML applications. Spanning 420 minutes, this professional-level course offers flexible subscription options, including Starter, Professional, and Paid plans, making it accessible to all aspiring data scientists and AI enthusiasts.

Anna Koop
Instructor

Anna Koop