Another dot in the blogosphere?

CrashCourse AI episode 8

Posted on: October 7, 2019

Video source

This week’s episode on artificial intelligence (AI) was a continuation of last week’s topic, natural language processing (NLP). The episode focused on an example of AI mimicking how a person might use words.

To do this, it introduced the concept of tokenisation — the process of breaking sentences up into words, spaces, punctuation, etc. This was just the first insight on how AI “understands” words and sentences.

The rest was complicated, e.g., words are reduced to numbers and associated with one another via vectors and matrices. The bottomline seemed to be that AI compared its predicted word use with actual word use from a large data set of written or spoken word from a person.

The episode left me with this thought: I appreciate how AI negotiates “meaning” statistically in an attempt to stimulate how we do so contextually and semantically.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Click to see all the nominees!

QR code

Get a mobile QR code app to figure out what this means!

My tweets


Usage policy

%d bloggers like this: