{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

2010exer1 - TAMPERE U NIVERSITY OF T ECHNOLOGY Department...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
T AMPERE U NIVERSITY OF T ECHNOLOGY Department of Software Systems OHJ-2556 Artificial Intelligence Exercises 1 prof. Tapio Elomaa Spring 2010 1. Every year the Loebner prize is awarded to the program that comes closest to passing a version of the Turing test. Research and report on the latest winner of the Loebner prize. What techniques does it use? How does it advance the state of the art in AI? 2. Is the intelligent agent approach chosen in the textbook sufficient for descri- bing all real-world phenomena? Which are the cases that support the approach? Which points, on the other hand, speak against it? 3. A neuron is a threshold unit that fires (is “on”) if the sum of its inputs is larger than its threshold value. The inputs come from other neurons or as external input. Let a neuron have binary states (0 or 1). The value that an edge transmits is the state of the start neuron × the weight of the edge. Logical variables take on binary values: 1 (true) or 0 (false). Design neuron networks implementing logical connectives
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}