Pruning (artificial neural network): Difference between revisions

Revision as of 15:38, 2 January 2025

Revision as of 21:03, 29 March 2025

Line 1:

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

{{other uses|Pruning (disambiguation)}}

In [[deep learning]], '''Pruningpruning''' is the practice of removing [[parameter]]s (which may entail removing individual parameters, or parameters in groups such as by [[artificial neurons|neurons]]) from an existing [[artificialNeural neuralnetwork network(machine learning)|artificial neural networksnetwork]].<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 maintain accuracy ofreduce the networksize while(parameter increasingcount) itsof [[efficiency]].the Thisneural cannetwork be(and done to reducetherefore the [[computational resource]]s required to run theit) neuralwhilst networkmaintaining accuracy. AThis can be compared to the biological process of [[synaptic pruning]] which takes place in the brain of[[Mammal|mammalian]] mammalsbrains 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}}</ref> (see also [[Neural Darwinism]]).

== Node (neuron) pruning ==

Line 11:

== 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}}</ref>

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}}</ref>

== See also ==

* [[Knowledge distillation]]

* [[Neural Darwinism]]

== References ==

Line 18 ⟶ 21:

[[Category:Artificial neural networks]]

{{Compu-ai-stub}}