A Similarity-based Normative Framework for Bio-plausible Neural Nets
Konferencijski prilog (Objavljena verzija)
,
© 2023 Institute of Molecular Genetics and Genetic Engineering, University of Belgrade
Metapodaci
Prikaz svih podataka o dokumentuApstrakt
In the last decade, Artificial Neural Nets (ANNs), rebranded as Deep Learning, have
revolutionized the field of Artificial Intelligence. While these neural nets have their origin
in analogy with the neural networks in the brain, in many ways they are trained in ways
that are very different from how real neurons learn. For example, to date there is no
satisfactory biologically plausible mechanism for backpropagation, the workhorse for
training ANNs.
Motivated by this gap, we have looked at alternative normative approaches to neural
networks that could give rise to more plausible learning rules. One such approach, which
works rather well for representation learning problems, is based on similarity matching
or kernel alignment. In this approach, one demands that similar sensory inputs produce
similar neural activities. From this rather limited constraint, one can give rise to interesting
neural networks performing many common unsupervised learning tasks. I will illustrate,
in ...particular, the case of representing continuous manifolds like spatial information. Here
, this approach produces representations very much like place cells in the hippocampus.
Consequences of our theory and its relations to some experiments would be discussed.
Time permitting, I would touch upon the role of similarity matching in current work in
ANNs as well.
Ključne reči:
neural network / brain representation learningIzvor:
4th Belgrade Bioinformatics Conference, 2023, 4, 18-18Izdavač:
- Belgrade : Institute of molecular genetics and genetic engineering
Finansiranje / projekti:
- I acknowledge long and fruitful collaborations with Yanis Bahroun, Dmitri Chklovskii, Alexander Genkin, Cengiz Pehlevan, Shagesh Shridharan and Mariano Tepper that have informed my view. This work was partly supported by a grant (SF 626323) to the author from the Simons Foundation.
Napomena:
- Book of abstract: 4th Belgrade Bioinformatics Conference, June 19-23, 2023
Kolekcije
Institucija/grupa
Institut za molekularnu genetiku i genetičko inženjerstvoTY - CONF AU - Sengupta, Anirvan PY - 2023 UR - https://belbi.bg.ac.rs/ UR - https://imagine.imgge.bg.ac.rs/handle/123456789/1953 AB - In the last decade, Artificial Neural Nets (ANNs), rebranded as Deep Learning, have revolutionized the field of Artificial Intelligence. While these neural nets have their origin in analogy with the neural networks in the brain, in many ways they are trained in ways that are very different from how real neurons learn. For example, to date there is no satisfactory biologically plausible mechanism for backpropagation, the workhorse for training ANNs. Motivated by this gap, we have looked at alternative normative approaches to neural networks that could give rise to more plausible learning rules. One such approach, which works rather well for representation learning problems, is based on similarity matching or kernel alignment. In this approach, one demands that similar sensory inputs produce similar neural activities. From this rather limited constraint, one can give rise to interesting neural networks performing many common unsupervised learning tasks. I will illustrate, in particular, the case of representing continuous manifolds like spatial information. Here , this approach produces representations very much like place cells in the hippocampus. Consequences of our theory and its relations to some experiments would be discussed. Time permitting, I would touch upon the role of similarity matching in current work in ANNs as well. PB - Belgrade : Institute of molecular genetics and genetic engineering C3 - 4th Belgrade Bioinformatics Conference T1 - A Similarity-based Normative Framework for Bio-plausible Neural Nets EP - 18 SP - 18 VL - 4 UR - https://hdl.handle.net/21.15107/rcub_imagine_1953 ER -
@conference{ author = "Sengupta, Anirvan", year = "2023", abstract = "In the last decade, Artificial Neural Nets (ANNs), rebranded as Deep Learning, have revolutionized the field of Artificial Intelligence. While these neural nets have their origin in analogy with the neural networks in the brain, in many ways they are trained in ways that are very different from how real neurons learn. For example, to date there is no satisfactory biologically plausible mechanism for backpropagation, the workhorse for training ANNs. Motivated by this gap, we have looked at alternative normative approaches to neural networks that could give rise to more plausible learning rules. One such approach, which works rather well for representation learning problems, is based on similarity matching or kernel alignment. In this approach, one demands that similar sensory inputs produce similar neural activities. From this rather limited constraint, one can give rise to interesting neural networks performing many common unsupervised learning tasks. I will illustrate, in particular, the case of representing continuous manifolds like spatial information. Here , this approach produces representations very much like place cells in the hippocampus. Consequences of our theory and its relations to some experiments would be discussed. Time permitting, I would touch upon the role of similarity matching in current work in ANNs as well.", publisher = "Belgrade : Institute of molecular genetics and genetic engineering", journal = "4th Belgrade Bioinformatics Conference", title = "A Similarity-based Normative Framework for Bio-plausible Neural Nets", pages = "18-18", volume = "4", url = "https://hdl.handle.net/21.15107/rcub_imagine_1953" }
Sengupta, A.. (2023). A Similarity-based Normative Framework for Bio-plausible Neural Nets. in 4th Belgrade Bioinformatics Conference Belgrade : Institute of molecular genetics and genetic engineering., 4, 18-18. https://hdl.handle.net/21.15107/rcub_imagine_1953
Sengupta A. A Similarity-based Normative Framework for Bio-plausible Neural Nets. in 4th Belgrade Bioinformatics Conference. 2023;4:18-18. https://hdl.handle.net/21.15107/rcub_imagine_1953 .
Sengupta, Anirvan, "A Similarity-based Normative Framework for Bio-plausible Neural Nets" in 4th Belgrade Bioinformatics Conference, 4 (2023):18-18, https://hdl.handle.net/21.15107/rcub_imagine_1953 .