Skip to playerSkip to main content
  • 2 years ago
Machine learning applications are ubiquitous. How does it work? This videographic answers. VIDEOGRAPHIC
Transcript
00:00 [Music plays]
00:07 Machine learning applications are ubiquitous.
00:10 We are using them on a daily basis, often without realising it.
00:13 On your smartphone alone, there are already countless applications.
00:17 When you log on, browse for products while shopping online,
00:21 check emails, type a text message, or plan a route.
00:25 So what is machine learning and how does it work under the hood?
00:28 It is a subfield of artificial intelligence that gives computers
00:31 the ability to learn without explicitly being programmed,
00:35 by enabling them to learn from data and experience.
00:38 Sometimes an algorithm can learn a task under supervision.
00:42 This involves using labelled data to train a model to make predictions or decisions.
00:48 It is used on online shopping to predict a user's preferences
00:51 based on historical data such as purchase history,
00:54 browsing behaviour, and product attributes,
00:58 and train a model to recommend products accordingly.
01:01 Other times, algorithms can learn without being supervised.
01:04 This involves identifying patterns and relationships in unstructured data
01:09 to create structure and categorisation.
01:11 It is used to cluster different products based on attributes
01:15 such as price, category, brand, and descriptions,
01:18 without labelled examples or guidance.
01:20 The goal is to find hidden structures and patterns
01:23 and identify similarities or differences between products.
01:27 Finally, sometimes algorithms learn from their own performance
01:30 and previous experiences as they adjust their behaviour
01:33 to improve the decision-making process.
01:35 This can be used to train a model to recommend products
01:38 that maximise user engagement or satisfaction
01:41 by recommending the right products to the right users.
01:44 Machine learning has a wide array of applications,
01:47 but it comes with ethical implications we need to consider
01:50 surrounding issues related to bias, fairness, accountability,
01:53 privacy, and transparency.
01:55 [Music plays]
01:57 [Music fades]
01:59 [Music fades]
02:01 [Music fades]
02:03 [BLANK_AUDIO]
Be the first to comment
Add your comment

Recommended