Artificial Neural Networks

Consider humans:

  $\mbox{$\bullet$}$

Neuron switching time ~ .001 second

  $\mbox{$\bullet$}$

Number of neurons ~ 10¹⁰

  $\mbox{$\bullet$}$

Connections per neuron ~ 10^4-5

  $\mbox{$\bullet$}$

Scene recognition time ~ .1 second

  $\mbox{$\bullet$}$

100 inference steps doesn't seem like enough

$\rightarrow$

much parallel computation

Properties of artificial neural nets (ANN's):

• Many neuron-like threshold switching units

• Many weighted interconnections among units

• Highly parallel, distributed process

• Emphasis on tuning weights automatically