COMP9444/9844 Neural Networks

Feedback Quiz on Tensor Product Networks

This is a voluntary quiz to help you decide whether you have understood some of the major concepts from this topic. It carries no marks.

  1. What does one-shot learning mean?

  2. Describe the role of binding units in a rank 2 tensor product network.

  3. Define a distributed representation.

  4. What does ΣiΣi bijvifj = 1 signify in a rank 2 tensor product network.

  5. Define a Hadamard matrix.

  6. How can a rank 3 tensor product network be used to store a relational fact like hit(max, frank)?

  7. Explain how a rank 3 tensor product network storing suitable relational facts can be used to solve a proportional analogy problem like dog : kennel :: rabbit : What?

  8. Explain the accessibility property of tensor product networks.

  9. What is a representable non-fact?

  10. What is a (dense) random representation?

Solutions: don't read until you've tried the questions yourself.

Bill Wilson's contact info

UNSW's CRICOS Provider No. is 00098G