Talk:Neuromorphic computing

External links

This mass of external links was removed from the article per the WP:EL guidelines. The list has been copied here for those who are interested but please do not restore them to the article.

Below is a list of leading researchers in various areas of neuromorphic engineering:

Vision and Robotics

• Geoffrey Barrows (Centeye Inc.)
• Kwabena Boahen (Stanford University)
• Eugenio Culurciello (Yale University)
• Tobi Delbruck, Shih-Chii Liu, and Giacomo Indiveri (ETH Zurich)
• Steve DeWeerth (Georgia Institute of Technology / Emory University)
• Ralph Etienne-Cummings (Johns Hopkins University)
• Bernabé Linares-Barranco and Teresa Serrano-Gotarredona (National Microelectronics Institute, Spain)
• Nicolas Franceschini (CNRS, France)
• Reid Harrison (University of Utah)
• Charles Higgins (University of Arizona)
• Timothy Horiuchi (University of Maryland)
• Rahul Sarpeshkar (Massachusetts Institute of Technology)
• Bertram Shi (Hong Kong University of Science and Technology)

Hearing, Sonar, and Speech Processing

• Andre van Schaik (University of Western Sydney)
• Andreas Andreou (Johns Hopkins)
• Gert Cauwenberghs (University of California, San Diego)
• Timothy Horiuchi and Shihab Shamma (University of Maryland)
• Rahul Sarpeshkar (Massachusetts Institute of Technology)
• John G. Harris, (Computational Neuroengineering Lab, University of Florida)

Neural Processing and Processing and Learning

• Andre van Schaik (University of Western Sydney)
• Gert Cauwenberghs (University of California, San Diego)
• Eugenio Culurciello (Yale University)
• Chris Diorio (University of Washington)
• Jennifer Hasler (Georgia Tech)
• Giacomo Indiveri (ETH Zurich)
• Sylvie Renaud (University of Bordeaux 1)
• Rahul Sarpeshkar (Massachusetts Institute of Technology)
• FACETS: Fast Analog Computing with Emergent Transient States (European Commission Research Project)
• Jose C. Principe, (Computational Neuroengineering Lab, University of Florida)
• Justin C. Sanchez, (Neuroprosthetics Research Group, University of Florida)
• Yong Chen, (University of California, Los Angeles)

Spike-Based Processing

• Andre van Schaik (University of Western Sydney)
• Kwabena Boahen (Stanford University)
• Giacomo Indiveri (ETH Zurich)
• Alan Murray and Alister Hamilton (University of Edinburgh)
• Tor Sverre Lande (University of Oslo)
• Shih-Chii Liu (ETH Zurich)
• Bernabé Linares-Barranco and Teresa Serrano-Gotarredona (National Microelectronics Institute, Spain)
• Sylvie Renaud (University of Bordeaux 1)
• Rahul Sarpeshkar (Massachusetts Institute of Technology)
• FACETS: Fast Analog Computing with Emergent Transient States (European Commission Research Project)
• John G. Harris, (Computational Neuroengineering Lab, University of Florida)
• Eugenio Culurciello (Yale University)

Biomedical and Ultra-Low-Power Applications

• Andre van Schaik (University of Western Sydney)
• Eugenio Culurciello (Yale University)
• John G. Harris, (Computational Neuroengineering Lab, University of Florida)
• Reid Harrison (University of Utah)
• Sylvie Renaud (University of Bordeaux 1)
• Rahul Sarpeshkar (Massachusetts Institute of Technology)
• Christofer Toumazou (Imperial College)

(See Leading Labs)

Other Links

• The Center for Neuromorphic Systems Engineering at the California Institute of Technology.
• The Computation and Neural Systems department at the California Institute of Technology.

Assessment

I'm responding to a request for reassessment from WP:WikiProject Neuroscience. I left it at Start Class, and rated it as Low Importance. Given the request, I'll comment on my reactions to the page. I think that it suffers from WP:NOTDICT and WP:SYNTH. It seems to me to start out as a dictionary-like definition of a term that is not particularly notable in the neuroscience literature, and then patches together a series of examples, without a clear indication that secondary sources regard these examples as being related by their belonging to this term. The most notable example given is the Human Brain Project, but it is unclear whether characterizing the project as being neuromorphic engineering is merely original research. Sorry for being harsh, but that's the way I see it. I hope that other editors will be able to improve the page. Alternatively, perhaps it should simply be merged into Computational neuroscience. --Tryptofish (talk) 22:17, 12 March 2013 (UTC)

Merge with Cognitive Computing

It has been suggested that Cognitive computing be merged into this article. (Discuss) Proposed since September 2014.

The article now appears with the banner above. I would like to oppose this change. If anything, the merge would be the other direction (as cognitive computing includes both neuromorphic computing and specific kinds of AI processing such as that done in the Watson system), but I would also oppose that. The two are now being treated in the research community as related topics with different uses - for example the Journal of Cognitive Computing will publish, but is not limited to, neuromorphic computing papers. The neural network literature does not publish papers on the more symbolic approaches, but do publish papers on using neural approaches to solve similar problems. I would thus suggest leaving these as separate articles that point at each other. JAHendler (talk) 00:31, 12 December 2014 (UTC)

Both the proposed merge to Cognitive computing and Physical neural network is equally weird. The first is about computing while the other is about physical engineering. Neuromorphic engineering (I prefer neuromorphic computing) is about how to do actual processing in available materials the way the brain does it. One can say that neuromorphic engineering/computing connects cognitive computing with physical engineering. Note that neural networks is a specific type of simplified early models for how the brain was supposed to work, and is not how the brain actually works. ;) Jeblad (talk) 18:01, 17 April 2016 (UTC)

I agree that the Cognitive computing merge doesn't make sense, since that article is talking about software algorithms for human–computer interaction, while this one is about hardware architectures that mimick neural networks. I've removed that merge tag. I'm inclined to support the merge from Physical neural network, though, since the subject matter of the articles seems identical. Antony–22 (^talk⁄_contribs) 19:16, 18 April 2016 (UTC)

Sorry, but Cognitive computing isn't about software algorithms for human–computer interaction. Let this be until someone that knows the field has time to look into it, I don't have the time right now. Jeblad (talk) 10:11, 20 April 2016 (UTC)

Well, I was going off of the definition in the lead of that article, which seems to have changed in the last two days. Now it's so vague I don't know what it is.

Upon further thought, physical neural networks are just one way to do neuromorphic computing, so perhaps they should stay as separate articles. But as it stands, the content of both articles is mainly lists of implementations of neuromorphic analog electronics, which should moved to either one article or the other. Antony–22 (^talk⁄_contribs) 17:37, 20 April 2016 (UTC)

Stochastic phase-change neurons

IBM Research in Zurich has created the world's first artificial nanoscale stochastic phase-change neurons.

Artificial neuromorphic systems based on populations of spiking neurons are an indispensable tool in understanding the human brain and in constructing neuromimetic computational systems.

Article URL: http://arstechnica.com/gadgets/2016/08/ibm-phase-change-neurons/

Study: http://www.nature.com/nnano/journal/v11/n8/full/nnano.2016.70.html — Preceding unsigned comment added by Kenorb (talk • contribs) 00:56, 6 August 2016 (UTC)

Neuromorphic

It could be worth nothing that some describe all kinds of low-power neuro-lookalike VLSI implementation as neuromorphic other believe that only implementations that utilize ideas from biological neurons should be said to be neuromporphic. In particular; an implementation that uses backprop algorithms is not based upon biological neurons as those use other means to reinforce learning at the synaptic level. Ie. backprop would imply learning at the neuron level, and in particular information flow upward along the axon. Jeblad (talk) 15:18, 21 April 2017 (UTC)

External links modified (February 2018)

Hello fellow Wikipedians,

I have just modified one external link on Neuromorphic engineering. Please take a moment to review my edit. If you have any questions, or need the bot to ignore the links, or the page altogether, please visit this simple FaQ for additional information. I made the following changes:

• Added archive https://web.archive.org/web/20130302142627/http://www.humanbrainproject.eu/partners.html to http://www.humanbrainproject.eu/partners.html

When you have finished reviewing my changes, you may follow the instructions on the template below to fix any issues with the URLs.

This message was posted before February 2018. After February 2018, "External links modified" talk page sections are no longer generated or monitored by InternetArchiveBot. No special action is required regarding these talk page notices, other than regular verification using the archive tool instructions below. Editors have permission to delete these "External links modified" talk page sections if they want to de-clutter talk pages, but see the RfC before doing mass systematic removals. This message is updated dynamically through the template {{source check}} (last update: 5 June 2024).

• If you have discovered URLs which were erroneously considered dead by the bot, you can report them with this tool.
• If you found an error with any archives or the URLs themselves, you can fix them with this tool.

Cheers.—InternetArchiveBot (Report bug) 14:49, 16 February 2018 (UTC)

Request to move mention of Intel Loihi from "See also" to "Examples"

Hello! I'd like to propose an update to this Wikipedia article. But first, a disclosure, which is also displayed in the connected contributor template above: I am submitting this request on behalf of Intel via Interfuse Communications, and as part of my work at Beutler Ink. Given my conflict of interest, I'm seeking volunteer editors to review and implement the proposed content appropriately, and I will not be editing the article directly.

Currently, the article's "Examples" section mentions work by several companies and institutions, including the Georgia Institute of Technology, MIT, Purdue, HP Labs, and IBM. "Intel Loihi" is currently displayed as a link within the "See also" section, but given the chip's significance and mentions in the AI accelerator and Cognitive computing entries, I believe a longer mention would provide useful information not currently found in the entry.

I propose removing the "See also" link and adding the following sentence to the "Examples" section:

Intel unveiled its neuromorphic research chip, called "Loihi", in October 2017. The chip uses an asynchronous spiking neural network (SNN) to implement adaptive self-modifying event-driven fine-grained parallel computations used to implement learning and inference with high efficiency.

References

This is a short description of the chip, which I believe is more beneficial to the article than a redirect in the "See also" section. I'd suggest placing this content at the end of the "Examples" section, since the last three paragraphs don't really have specific dates, but editors may prefer somewhere else to maintain chronology. Do other editors think this is an appropriate addition to the article? If so, feel free to copy and paste the following markup for easier implementation in the main space:

Markup

[[Intel]] unveiled its neuromorphic research chip, called "[[Intel Loihi|Loihi]]", in October 2017. The chip uses an asynchronous [[spiking neural network]] (SNN) to implement adaptive self-modifying event-driven fine-grained parallel computations used to implement learning and inference with high efficiency.<ref>{{cite journal |last1=Davies |first1=Mike |title=Loihi: A Neuromorphic Manycore Processor with On-Chip Learning |journal=IEEE Micro |date=January 16, 2018 |volume=38 |issue=1 |pages=82–99 |url=https://ieeexplore.ieee.org/document/8259423/ |accessdate=August 5, 2018 |display-authors=etal}}</ref><ref>{{cite web |last1=Hsu |first1=Jeremy |title=CES 2018: Intel's 49-Qubit Chip Shoots for Quantum Supremacy |url=https://spectrum.ieee.org/tech-talk/computing/hardware/intels-49qubit-chip-aims-for-quantum-supremacy |publisher=[[Institute of Electrical and Electronics Engineers]] |accessdate=August 5, 2018 |date=January 9, 2018}}</ref>

Let me know if you have any questions or concern, and thanks for your consideration. Inkian Jason (talk) 21:37, 6 August 2018 (UTC)

There is secondary coverage of this chip by now, at least in the popular press, so I would be comfortable adding a short description to the examples section. The second reference above is about quantum computers and just mentions Loihi in passing. Perhaps the ZDNet article would be a better alternative? It goes more in depth and compares it with other efforts like True North. --{{u|Mark viking}} {Talk} 19:16, 17 August 2018 (UTC)

@Mark viking: Thanks for reviewing. I am fine using your preferred sourcing. I don't edit the main space directly because of my COI. Do you mind updating the article appropriately? Inkian Jason (talk) 19:37, 17 August 2018 (UTC)

 Done --{{u|Mark viking}} {Talk} 23:28, 17 August 2018 (UTC)

@Mark viking: Thanks for your help. I noticed the text "hideMarkup" now appears in the article's prose, but otherwise the addition looks good. Inkian Jason (talk) 14:19, 20 August 2018 (UTC)

Fixed, thanks. --{{u|Mark viking}} {Talk} 17:40, 20 August 2018 (UTC)

@Mark viking: Thanks again! Inkian Jason (talk) 17:41, 20 August 2018 (UTC)

the language proposed has a bit too much jargon. but otherwise im not opposed to the idea of addin loihi and its derivative ssytems to the article iteslf.

The article contains editor commentary as part of its text. I didn't want to erase, but it doesn't look good. Can someone who is more familiar with the topic fix it? — Preceding unsigned comment added by 83.130.142.238 (talk) 08:05, 31 December 2020 (UTC)

Horrible introduction / definition

I just visited this wiki site to better understand what the term means. I am utterly confused by the intro / definition. This is just a gigantic pile of complex words! Can someone with expertise please clean this up and give tangible examples of what the term means in real world? No need for this insane aggregation of Scientific buzzwords! — Preceding unsigned comment added by 89.246.122.235 (talk) 17:02, 4 March 2021 (UTC)

I'll explain: a neuromorphic computer is just as the name sounds neuro = referring to the nervous system, morphic = like , neuromorphic = like the nervous system. A neuromorphic computer/chip is any device that uses physical artificial neurons (made from silicon) to do computations. there are many articles online written for the layman that expand on this topic if you would like to learn more. i do think your concern about the article is valid. RJJ4y7 (talk) 19:33, 29 June 2021 (UTC)

i fixed the issue RJJ4y7 (talk) 16:27, 6 October 2021 (UTC)

Dual use (military applications)

This section is oddly titled and lacks any references for its contents, even though it contains a direct quotation. Is anyone able to provide references and clarity for this section? TimberToner (talk) 05:31, 19 January 2023 (UTC)

Requested move 24 August 2024

The following is a closed discussion of a requested move. Please do not modify it. Subsequent comments should be made in a new section on the talk page. Editors desiring to contest the closing decision should consider a move review after discussing it on the closer's talk page. No further edits should be made to this discussion.

The result of the move request was: moved as requested per the discussion below. Dekimasuよ! 13:51, 6 September 2024 (UTC)

---

Neuromorphic engineering → Neuromorphic computing – WP:COMMONNAME. The current article title is "Neuromorphic engineering" but the opening sentence talks about "neuromorphic computing". An Ngram comparison confirms that "neuromorphic computing" is a much more commonly used term. The suggested target has redirected to this article since it was created in 2011. The word "computing" is used three times in the first two paragraphs, while "engineering" isn't mentioned until the third paragraph. —⁠ ⁠BarrelProof (talk) 00:19, 24 August 2024 (UTC) — Relisting. RodRabelo7 (talk) 01:42, 31 August 2024 (UTC)

Yes, "neuromorphic computing" is more common. Vacosea (talk) 02:20, 30 August 2024 (UTC)

Relisting comment: First relist. RodRabelo7 (talk) 01:42, 31 August 2024 (UTC)

Note: WikiProject Human rights, WikiProject Technology, WikiProject Computer science, WikiProject Engineering, WikiProject Neuroscience, and WikiProject Computing have been notified of this discussion. RodRabelo7 (talk) 01:51, 31 August 2024 (UTC)

• Support move. (I came here from the notice at WT:NEURO.) It looks to me like almost all of the engineering applications are for chips or circuits to be used for computing, so it does seem to be a primarily computing topic. --Tryptofish (talk) 21:13, 31 August 2024 (UTC)

I agree, Neuromorphic computing not only seems to be used more frequently, it would also more closely reflect the actual topic of the article, which appears to be more computing-oriented. Regards, SirBrahms (talk) 07:10, 3 September 2024 (UTC)

The discussion above is closed. Please do not modify it. Subsequent comments should be made on the appropriate discussion page. No further edits should be made to this discussion.