PSYC 421 Ch 5

A biological neuron has

A single axon and many dendrites

Which of the following is true of feedforward networks?

Activation spreads through the network in a series of discrete time steps corresponding to the number of layers.

All activation functions in artificial neural networks are linear

False

All learning algorithms for multilayers networks require supervision and feedback.

False

Any Boolean function can be represented by a single-layer network?

False

Perceptron convergence learning does not require feedback about error

False

The Boolean function XOR (exclusive OR) assigns which truth value to the input pair (TRUE, TRUE)?

False

The perceptron convergence learning rule can be used for both single-layer and multi-layer networks. It is also present in FB face recognition software.

False

"Neurons that wire together, fire together" is a description of which type of learning?

Hebbian learning

How does an artificial neural network store information?

In the pattern of weights holding across individual units

Which of the following mathematical operations is not a function?

Taking square roots

The aim of neural network modeling is --

To approximate the behavior of populations of neurons

Artificial neural network units with the same inputs but different activation functions can have different outputs

True

The Boolean function OR (inclusive OR) assigns which truth value to the input pair (TRUE, TRUE)?

True

The Boolean function XOR cannot be represented by a single-layer network because it is not linearly separable.

True

There is no clear distinction between information storage and information processing in artificial neural network models

True

Boolean functions are defined over --

Truth values

Which type of learning rule can work for networks with hidden units?

backpropagation of error

A sending neuron's axon comes close to a receiving neuron's dendrite at

synapse

Which of the following types of learning is supervised?

the backpropagation algorithm