Lightning AI Studios: Never set up a local environment again →

Log in or create a free Lightning.ai account to track your progress and access additional course materials  

1.1 What Is Machine Learning?

What we covered in this video lecture

In this video, we saw some real-world applications of machine learning. Yes, like it or not, it is almost everywhere in our daily lives, and this is an excellent reason to learn more about it! One of the most popular subcategories of machine learning revolves around learning from data to make predictions (we will learn more about it later).

In addition, we learned that machine learning is a subcategory of AI. AI is a field of research focused on making computers behave smarter ways. Machine learning provides the techniques to teach computers how to learn from data. In turn, deep learning is a subcategory of machine learning centered around training deep neural networks. (Deep learning and training deep neural networks will be the focus of this course!)

Are you curious to see more applications of machine learning? Check out the Applications section of the Wikipedia article on machine learning. Or, if you are curious about the history of AI, check out this very comprehensive article.

Note that deep learning is sometimes used nowadays for tabular data. You can find more resources about that in the following article:

Log in or create a free Lightning.ai account to access:

  • Quizzes
  • Completion badges
  • Progress tracking
  • Additional downloadable content
  • Additional AI education resources
  • Notifications when new units are released
  • Free cloud computing credits

Quiz: 1.1 What Is Machine Learning? Part 1

Does a search engine (like Google) use machine learning?

This is correct, Google search employes several techniques in their search algorithm, from learning how to rank the results to parsing the language queries

This is incorrect, Google search employes several techniques in their search algorithm, from learning how to rank the results to parsing the language queries.

Predicting whether a given email is “spam” or “not spam” is a task that is typically done by a machine learning classifier.

This is correct. Spam labeling is a typical classification task where the machine learning algorithm learns from labeled data.

This is incorrect. While this task could be solved without machine learning as well, Spam labeling is a typical classification task where the machine learning algorithm learns from labeled data.

Estimating the population size of a country from census data is a typical machine learning task.

Incorrect. Accounting and statistical inference is sufficient to determine the population size from data samples.

Correct. accounting and statistical inference is sufficient to determine the population size from data samples.

Machine learning lets computers learn from … (Check all that are correct)

Correct, the premise behind machine learning is to let computers learn automatically from data.

Correct. In many cases, we provide labeled examples to learn prediction tasks. However, unlabeled data is often used for machine learning as well.

Typically, machine learning algorithms learn from data, not programs. In fact, the machine learning models take place of complicated programs (e.g., programs that determine the zip code from handwriting.)

Please answer all questions to proceed.

Quiz: 1.1 What Is Machine Learning? Part 2

Machine learning is a subfield of … (Check all terms that apply.)

Incorrect, deep learning is a subfield of machine learning, not the other way around.

Correct, machine learning originally emerged as a field within AI with the premise for AI to learn from data (as opposed to being programmed manually).

Deep learning excels on

Incorrect. “Structured” can have different meanings, but in machine learning contexts, it typically refers to table- or spreadsheet-like data derived from manual feature engineering. Deep learning excels at problems where it learns from raw (unstructured) data and performs the feature extraction implicitely.

Correct.

Please answer all questions to proceed.
Watch Video 1

Unit 1.1

Videos
Questions or Feedback?

Join the Discussion