Language:

Towards deep learning with segregated dendrites

eLife, 2017-12, Vol.6 [Peer Reviewed Journal]

2017, Guerguiev et al. This work is licensed under the Creative Commons Attribution License ( https://creativecommons.org/licenses/by/3.0/ ) (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;2017, Guerguiev et al 2017 Guerguiev et al ;ISSN: 2050-084X ;EISSN: 2050-084X ;DOI: 10.7554/eLife.22901 ;PMID: 29205151

Full text available

Citations Cited by

Actions
1. Add to My Research
2. Remove from My Research
3. E-mail
4. Print
5. Permalink
6. Citation
7. EasyBib
8. EndNote
9. RefWorks
10. Delicious
11. Export RIS
12. Export BibTeX

Title:
Towards deep learning with segregated dendrites
Author: Guerguiev, Jordan ; Lillicrap, Timothy P ; Richards, Blake A
Subjects: Algorithms ; Artificial Intelligence ; Back propagation ; Behavior ; Brain ; Computational and Systems Biology ; credit assignment ; deep learning ; Dendrites ; dendritic morphology ; Expected values ; feedback alignment ; Machine Learning ; Models, Neurological ; Neocortex ; Neural Networks (Computer) ; Neuroscience ; Neurosciences ; Pyramidal cells ; Synaptic strength ; target propagation
Is Part Of: eLife, 2017-12, Vol.6
Description: Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep learning algorithm that utilizes multi-compartment neurons might help us to understand how the neocortex optimizes cost functions. Like neocortical pyramidal neurons, neurons in our model receive sensory information and higher-order feedback in electrotonically segregated compartments. Thanks to this segregation, neurons in different layers of the network can coordinate synaptic weight updates. As a result, the network learns to categorize images better than a single layer network. Furthermore, we show that our algorithm takes advantage of multilayer architectures to identify useful higher-order representations-the hallmark of deep learning. This work demonstrates that deep learning can be achieved using segregated dendritic compartments, which may help to explain the morphology of neocortical pyramidal neurons.
Publisher: England: eLife Sciences Publications Ltd
Language: English
Identifier: ISSN: 2050-084X
EISSN: 2050-084X
DOI: 10.7554/eLife.22901
PMID: 29205151
Source: MEDLINE
PubMed Central
ROAD: Directory of Open Access Scholarly Resources
ProQuest Central
DOAJ Directory of Open Access Journals

Back to results list


INSPIRE LIBRARY - TON DUC THANG UNIVERSITY	(84-028) 37 755 057	Feedback
19 Nguyen Huu Tho St. Dist.7, HCM	thuvien@tdtu.edu.vn	Feedback

Towards deep learning with segregated dendrites

Searching Remote Databases, Please Wait