finite impulse response

Terms from Artificial Intelligence: humans at the heart of algorithms

The glossary is being gradually proof checked, but currently has many typos and misspellings.

In a finite input response (FIR) system observations or events far enough in the past have no effect on the current behaviour of the system. Typically this is true of systems that use a fixed window over the data of, say, the last N items and base responses only on these. However, this may also be less obvious. Some statistical time series analysis techniques are FIR such as a moving average as well as window-based neural networks.

FIR is in contrast to infinite impluse response (IIR) systems where there is no limit on how far backward data influences persist.

Note that while most {LLM}}s use a fixed window, so are strictly FIR, the window is often larger than a complete data sequence, so they is therefore effecitively IIR.

Used in Chap. 14: pages 206, 210, 216

Also known as FIR