Pruning (artificial neural network): Difference between revisions

Revision as of 20:22, 7 June 2020

Latest revision as of 18:18, 26 June 2025

(30 intermediate revisions by 22 users not shown)

Line 1:

{{Short description|Trimming artificial neural networks to reduce computational overhead}}

{{Orphan|date=June 2020}}

{{other uses|Pruning (disambiguation)}}

In the context of [[artificial neural network]], '''pruning''' is the practice of removing [[artificial neurons]] after learning, usually with the goal of reducing the computational resources required to run the neural network. A basic algorithm for pruning is as follows<ref>Molchanov, P., Tyree, S., Karras, T., Aila, T., & Kautz, J. (2016). ''Pruning convolutional neural networks for resource efficient inference''. arXiv preprint arXiv:1611.06440.</ref><ref>[https://jacobgil.github.io/deeplearning/pruning-deep-learning Pruning deep neural networks to make them fast and small].</ref>:

In [[deep learning]], '''pruning''' is the practice of removing [[parameter]]s from an existing [[Neural network (machine learning)|artificial neural network]].<ref>{{cite arXiv|last1=Blalock|first1=Davis|last2=Ortiz|first2=Jose Javier Gonzalez|last3=Frankle|first3=Jonathan|last4=Guttag|first4=John|date=2020-03-06|title=What is the State of Neural Network Pruning?|class=cs.LG|eprint=2003.03033}}</ref> The goal of this process is to reduce the size (parameter count) of the neural network (and therefore the [[computational resource]]s required to run it) whilst maintaining accuracy. This can be compared to the biological process of [[synaptic pruning]] which takes place in [[Mammal|mammalian]] brains during development.<ref>{{Cite journal |last1=Chechik |first1=Gal |last2=Meilijson |first2=Isaac |last3=Ruppin |first3=Eytan |date=October 1998 |title=Synaptic Pruning in Development: A Computational Account |url=https://ieeexplore.ieee.org/document/6790725 |journal=Neural Computation |volume=10 |issue=7 |pages=1759–1777 |doi=10.1162/089976698300017124 |pmid=9744896 |s2cid=14629275 |issn=0899-7667|url-access=subscription }}</ref>

== Node (neuron) pruning ==

In the context of [[artificial neural network]], '''pruning''' is the practice of removing [[artificial neurons]] after learning, usually with the goal of reducing the computational resources required to run the neural network. A basic algorithm for pruning is as follows:<ref>Molchanov, P., Tyree, S., Karras, T., Aila, T., & Kautz, J. (2016). ''Pruning convolutional neural networks for resource efficient inference''. arXiv preprint arXiv:1611.06440.</ref><ref>[https://jacobgil.github.io/deeplearning/pruning{{Cite web |last=Gildenblat |first=Jacob |date=2017-deep06-learning23 |title=Pruning deep neural networks to make them fast and small] |url=http://jacobgil.github.io/deeplearning/pruning-deep-learning |access-date=2024-02-04 |website=Github |language=en}}</ref>:

#Evaluate the importance of each neuron.

#Rank the neurons according to their importance (assuming there is a clearly defined measure for "importance").

#Remove the least important neuron.

#Check a termination condition (to be determined by the user) to see whether to continue pruning.

== Edge (weight) pruning ==

Most work on neural network pruning focuses on removing weights, namely, setting their values to zero. Early work suggested to also change the values of non-pruned weights.<ref>{{Cite journal |last1=Chechik |first1=Gal |last2=Meilijson |first2=Isaac |last3=Ruppin |first3=Eytan |date=April 2001 |title=Effective Neuronal Learning with Ineffective Hebbian Learning Rules |url=https://ieeexplore.ieee.org/document/6789989 |journal=Neural Computation |volume=13 |issue=4 |pages=817–840 |doi=10.1162/089976601300014367 |pmid=11255571 |s2cid=133186 |issn=0899-7667|url-access=subscription }}</ref>

== See also ==

* [[Knowledge distillation]]

* [[Neural Darwinism]]

== References ==

{{reflist}}

[[Category:Artificial neural networks]]

{{Compu-ai-stub}}

{{Compudeep-ailearning-stub}}

[[Category:Artificial neural networks]]