How the machines work

Member lesson

Multimodal models

Lesson 11 of 13 in How the machines work.

What Are Vision Language Models? How AI Sees & Understands Images · IBM Technology
Lesson

A model that can see changes what you can ask it. Hand it the client's existing photography and ask what the lighting has in common, and you get an answer in a minute that would have taken an afternoon of looking. Hand it a competitor's shelf and ask what the category conventions are. Hand it your own forty frames and ask which three do not belong.

A person in round glasses sits in front of a wall of pinned photographs, pointing confidently at how the light falls in them while writing in a notebook. Their lenses are smudged, and the small colour chip on the nearest photo is blurred.
Quick to read a whole wall of pictures, poor at the small print. Measure colour and type instead.
Member

The rest of this is for members.

You have read the opening of this lesson. The rest of it comes with a membership.

One membership covers all four courses and Brands.

  • All lessons in the four Learn courses
  • All brand breakdowns in the Brands section
  • All quizzes, flashcards and crosswords
  • An AI teacher on every lesson, for up to 60 questions a day
  • All course material published during the membership

Price

Membership is from $12 a month on the Yearly plan, which is charged at $144 once a year. Lifetime access is $59, paid once.Membership is from ₹200 a month on the Yearly plan, which is charged at ₹2,400 + GST once a year. Lifetime access is ₹3,999 + GST, paid once.

Check what stuck

Members only

You can't take this check yet.

Members answer these 3 questions and keep the ticket for this lesson. Every lesson has one.

  1. Question 1, locked

    Which of these words means this? “A model that takes more than one kind of input: text and images, sometimes audio and video.”

    • Multimodal
    • Fine-tuning
    • Benchmark
    • Embedding
  2. Question 2, locked

    Which of these words means this? “One that can look at a picture and answer questions about it.”

    • Sample
    • Determinism
    • Per-image cost
    • Vision model
  3. Question 3, locked

    Which of these words means this? “Tying an answer to something the model can actually see, rather than to what it generally knows.”

    • Unit economics
    • Head
    • Multimodal
    • Grounding

Elsewhere in the library

Hear about new courses.

Leave an email and we will tell you when something new lands. We do not write often.