Connectionists: Scientific Integrity, the 2021 Turing Lecture, etc.
Tsvi Achler
achler at gmail.com
Wed Nov 10 18:33:42 EST 2021
Dear Juyang & Ali
Modularity and localized learning does not work with feedforward networks,
but it works within networks where neurons inhibit their own inputs, like
Regulatory Feedback.
Each neuron can be configured as an individual unit and the weights can be
the value of inputs present when a supervised signal is given. This
is localized learning e.g. representing likelihood without distribution or
the original simple Hebbian type learning without normalization or
adjustment based on error.
The key to regulatory feedback is that for each input a neuron receives it
sends an inhibitory projection linked to its activation to that same input
(e.g. by connecting back to inhibitory interneurons).
Neurons in the regulatory feedback configuration are modular, you
can include them or not include them in the network and they can even be
dynamically taken out anytime by artificially forcing a neuron activation
to be zero during recognition iterations.
When recognizing the iterative feedback interactions between neurons
cooperatively and competitively determines which neurons are the best fit
to the input. The iterations during recognition are the "glue" that allows
modular neurons to interact together to find the best result that includes
the contribution (and updated contributions) of all of the modular neurons.
Thus the results of recognition are distributed via potential contributions
of many neurons but the learning is localized.
I know initially this is very counterintuitive and foreign but I encourage
you to understand the mechanism and results through the videos and papers
before making statements that: modularity is not possible or "too simple".
It is just not possible or clear in feedforward networks.
Two papers where I analyze the modularity are:
1) Achler T., Non-Oscillatory Dynamics to Disambiguate Pattern Mixtures,
Chapter 4 in Relevance of the Time Domain to Neural Network Models, Eds:
Rao R, Cecchi G A, pp 57-74, Springer 2011
which builds up a network by adding nodes, and also introduces potential
scenarios of linear dependence I described in my previous message
2) Achler T., Amir E., Input Feedback Networks: Classification and
Inference Based on Network Structure, Artificial General Intelligence, V1:
15-26, IOS 2008.
an even older paper which discusses adding modular nodes ad infinitum and
their continued contribution to the network. This paper goes back to when
I used a binary weight version which I called Input Feedback Networks and
did not use the terms modular, but concepts and mathematics apply.
I am happy to forward the pdf copies to those who ask for them.
Video playlist:
https://www.youtube.com/playlist?list=PL4nMP8F3B7bg3cNWWwLG8BX-wER2PeB-3
Sincerely,
-Tsvi
On Wed, Nov 10, 2021 at 12:41 AM Juyang Weng <juyang.weng at gmail.com> wrote:
> Dear Ali,
>
> I agree "localized vs. distributed" as a dichotomy is too simple, as I
> discussed with Asim before.
>
> However, "importance of modularity" is just a slightly higher level
> mistake from people who worked on "neuroscience" experiments, of the same
> nature as the "localized vs. distributed" dichotomy. "Localized vs.
> distributed" is too simple; "modularity" is also too simple to be true
> too. Unfortunately, neuroscientists have spent time on many experiments
> whose answers have already been predicted by our Developmental Networks
> (DN), especially DN-2.
>
> However, there is one known model that is holistic in terms
> of general-purpose computing. That is Universal Turing machines, although
> they were not for brains to start with. Researchers in this challenging
> brain subject did not seem to pay sufficient attention to the emergent
> Universal Turing Machine (in our Developmental Networks) as a holistic
> model of an entire brain. If we look into how excitatory cells and
> inhibitory sells migrate and connect, as I explained in my NAI book,
>
> https://www.amazon.com/Natural-Artificial-Intelligence-Juyang-Weng/dp/0985875712
> it is impossible to have brain modules as you stated.
>
> If we insist on our discussion on Brodmann areas, then Brodmann areas are
> primarily resource areas (like, not exactly the same as, registers, cash,
> RAM, and disks) not functional areas. DN-1 has modules, but not
> functional modules, but resource modules. DN-2 is more correct in that
> even the boundaries of resource modules are adaptive. Some lower brain
> areas synthesize specific types of neuro-transmitters (as explained in my
> book above), e.g., serotonin, but such areas are still resource modules,
> not brain-function models. A brain uses serotonin for many different
> functions.
>
> In summary, no Brodmann areas should be assigned to any specific brain
> functions (like edges, but resources), including lower brain areas, such as
> raphe nuclei (that synthesize serotonin) and hippocampus (also resources,
> not functions). Your cited examples are well known and support my above
> fundamental view, backed up by DN as a full algorithmic model of the entire
> brain (not brain modules).
> That is, "place cells" are a misnomer.
>
> I am writing something sensitive. I hope this connectionist at cmu will not
> reject it.
>
> Best regards,
> -John
>
> On Tue, Nov 9, 2021 at 2:55 AM Ali Minai <minaiaa at gmail.com> wrote:
>
>> Asim
>>
>> This is a perennial issue, but I don't think one should see "localized
>> vs. distributed" as a dichotomy. Neurons (or groups of neurons) all over
>> the brain are obviously tuned to specific things in specific contexts -
>> place cells are an obvious example, as are the cells in orientation
>> columns, and indeed, much of the early visual system. That's why we can
>> decode place from hippocampal recordings in dreaming rats. But in many
>> cases, the same cells are tuned to something else in another context
>> (again, think of place cells). The notion of "holographically" distributed
>> representations is a nice abstract idea but I doubt if it applies anywhere
>> in the brain. However, any object/concept, etc., is better represented by
>> several units (neurons, columns, hypercolumns, whatever) than by a single
>> one, and in a way that makes these representations both modular and
>> redundant enough to ensure robustness. Two old but still very interesting
>> papers in this regard are:
>>
>> Tsunoda K, Yamane Y, Nishizaki M, & Tanifuji M (2001) Complex objects
>> are represented in macaque inferotemporal cortex by the combination of
>> feature columns. Nat Neurosci 4:832–838.
>>
>>
>> Wang, G., Tanaka, K. & Tanifuji M (2001) Optical imaging of functional
>> organization in the monkey inferotemporal cortex. Science 272:1665-1668.
>>
>>
>> If there's one big lesson biologists have learned in the last 50 years,
>> it is the importance of modularity - not in the Fodorian sense but in the
>> sense of Herb Simon, Jordan Pollack, et al. The more we think of the brain
>> as a complex system, the clearer the importance of modularity and synergy
>> will become. If all other complex systems exploit multi-scale modularity
>> and synergistic coordination to achieve all sorts of useful attributes,
>> it's inconceivable that the brain does not. Too much of AI - including
>> neural networks - has been oblivious to biology, and too confident in the
>> ability of abstractions to solve very complicated problems. The only way
>> "real" AI will be achieved is by getting much closer to biology - not just
>> in the superficial use of brain-like neural networks, but with much deeper
>> attention to all aspects of the biological processes that still remain the
>> only producers to intelligence known to us.
>>
>>
>> Though modular representations can lead to better explainability to a
>> limited degree (again, think of the dreaming rat), I am quite skeptical
>> about "explainable AI" in general. Full explainability (e.g., including
>> explainability of motivations) implies reductionistic analysis, but true
>> intelligence will always be emergent and, by definition, quite full of
>> surprises. The more "explainable" we try to make AI, the more we are
>> squeezing out exactly that emergent creativity that is the hallmark of
>> intelligence. Of course, such a demand is fine when we are just building
>> machine learning-based tools for driving cars or detecting spam, but that
>> is far from true general intelligence. We will only have built true AI when
>> the thing we have created is as mysterious to us in its purposes as our cat
>> or our teenage child :-). But that is a whole new debate.
>>
>>
>> The special issue sounds like an interesting idea.
>>
>>
>> Cheers
>>
>>
>> Ali
>>
>>
>>
>> *Ali A. Minai, Ph.D.*
>> Professor and Graduate Program Director
>> Complex Adaptive Systems Lab
>> Department of Electrical Engineering & Computer Science
>> 828 Rhodes Hall
>> University of Cincinnati
>> Cincinnati, OH 45221-0030
>>
>> Past-President (2015-2016)
>> International Neural Network Society
>>
>> Phone: (513) 556-4783
>> Fax: (513) 556-7326
>> Email: Ali.Minai at uc.edu
>> minaiaa at gmail.com
>>
>> WWW: https://eecs.ceas.uc.edu/~aminai/ <http://www.ece.uc.edu/%7Eaminai/>
>>
>>
>> On Sun, Nov 7, 2021 at 2:15 PM Asim Roy <ASIM.ROY at asu.edu> wrote:
>>
>>> All,
>>>
>>>
>>>
>>> Amir Hussain, Editor-in-Chief, Cognitive Computation, is inviting us to
>>> do a special issue on the topics under discussion here. They could be short
>>> position papers summarizing ideas for moving forward in this field. He
>>> promised reviews within two weeks. If that works out, we could have the
>>> special issue published rather quickly.
>>>
>>>
>>>
>>> Please email me if you are interested.
>>>
>>>
>>>
>>> Asim Roy
>>>
>>> Professor, Arizona State University
>>>
>>> Lifeboat Foundation Bios: Professor Asim Roy
>>> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com%2Fv3%2F__https%3A%2Flifeboat.com%2Fex%2Fbios.asim.roy__%3B!!IKRxdwAv5BmarQ!JYoK0hORlllDPMK5nxG1MV8TRdHc4uGvWM3awogw4qslieKdtCnnX7G9gvkI0Xg%24&data=04%7C01%7Cminaiaa%40ucmail.uc.edu%7Cfb6eeb2f02f04eb8ba0808d9a28c2aad%7Cf5222e6c5fc648eb8f0373db18203b63%7C1%7C0%7C637719545203903472%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=JdP4yxlo3TIWNkbI%2BarQqelCr4e2ErpXJN0bm2uIFw8%3D&reserved=0>
>>>
>>>
>>>
>>> *From:* Yoshua Bengio <yoshua.bengio at mila.quebec>
>>> *Sent:* Sunday, November 7, 2021 8:55 AM
>>> *To:* Asim Roy <ASIM.ROY at asu.edu>
>>> *Cc:* Adam Krawitz <akrawitz at uvic.ca>; connectionists at cs.cmu.edu;
>>> Juyang Weng <juyang.weng at gmail.com>
>>> *Subject:* Re: Connectionists: Scientific Integrity, the 2021 Turing
>>> Lecture, etc.
>>>
>>>
>>>
>>> Asim,
>>>
>>>
>>>
>>> You can have your cake and eat it too with modular neural net
>>> architectures. You still have distributed representations but you have
>>> modular specialization. Many of my papers since 2019 are on this theme. It
>>> is consistent with the specialization seen in the brain, but keep in mind
>>> that there is a huge number of neurons there, and you still don't see
>>> single grand-mother cells firing alone, they fire in a pattern that is
>>> meaningful both locally (in the same region/module) and globally (different
>>> modules cooperate and compete according to the Global Workspace Theory and
>>> Neural Workspace Theory which have inspired our work). Finally, our recent
>>> work on learning high-level 'system-2'-like representations and their
>>> causal dependencies seeks to learn 'interpretable' entities (with natural
>>> language) that will emerge at the highest levels of representation (not
>>> clear how distributed or local these will be, but much more local than in a
>>> traditional MLP). This is a different form of disentangling than adopted in
>>> much of the recent work on unsupervised representation learning but shares
>>> the idea that the "right" abstract concept (related to those we can name
>>> verbally) will be "separated" (disentangled) from each other (which
>>> suggests that neuroscientists will have an easier time spotting them in
>>> neural activity).
>>>
>>>
>>>
>>> -- Yoshua
>>>
>>>
>>>
>>> *I'm overwhelmed by emails, so I won't be able to respond quickly or
>>> directly. Please write to my assistant in case of time sensitive matter or
>>> if it entails scheduling: julie.mongeau at mila.quebec
>>> <julie.mongeau at mila.quebec>*
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>> Le dim. 7 nov. 2021, à 01 h 46, Asim Roy <ASIM.ROY at asu.edu> a écrit :
>>>
>>> Over a period of more than 25 years, I have had the opportunity to argue
>>> about the brain in both public forums and private discussions. And they
>>> included very well-known scholars such as Walter Freeman (UC-Berkeley),
>>> Horace Barlow (Cambridge; great grandson of Charles Darwin), Jay McClelland
>>> (Stanford), Bernard Baars (Neuroscience Institute), Christof Koch (Allen
>>> Institute), Teuvo Kohonen (Finland) and many others, some of whom are on
>>> this list. And many became good friends through these debates.
>>>
>>>
>>>
>>> We argued about many issues over the years, but the one that baffled me
>>> the most was the one about localist vs. distributed representation. Here’s
>>> the issue. As far as I know, although all the Nobel prizes in the field of
>>> neurophysiology – from Hubel and Wiesel (simple and complex cells) and
>>> Moser and O’Keefe (grid and place cells) to the current one on discovery of
>>> temperature and touch sensitive receptors and neurons - are about finding
>>> “meaning” in single or a group of dedicated cells, the distributed
>>> representation theory has yet to explain these findings of “meaning.”
>>> Contrary to the assertion that the field is open-minded, I think most in
>>> this field are afraid the to cross the red line.
>>>
>>>
>>>
>>> Horace Barlow was the exception. He was perhaps the only neuroscientist
>>> who was willing to cross the red line and declare that “grandmother cells
>>> will be found.” After a debate on this issue in 2012, which included Walter
>>> Freeman and others, Horace visited me in Phoenix at the age of 91 for
>>> further discussion.
>>>
>>>
>>>
>>> If the field is open minded, would love to hear how distributed
>>> representation is compatible with finding “meaning” in the activations of
>>> single or a dedicated group of cells.
>>>
>>>
>>>
>>> Asim Roy
>>>
>>> Professor, Arizona State University
>>>
>>> Lifeboat Foundation Bios: Professor Asim Roy
>>> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com%2Fv3%2F__https%3A%2Flifeboat.com%2Fex%2Fbios.asim.roy__%3B!!IKRxdwAv5BmarQ!JYoK0hORlllDPMK5nxG1MV8TRdHc4uGvWM3awogw4qslieKdtCnnX7G9gvkI0Xg%24&data=04%7C01%7Cminaiaa%40ucmail.uc.edu%7Cfb6eeb2f02f04eb8ba0808d9a28c2aad%7Cf5222e6c5fc648eb8f0373db18203b63%7C1%7C0%7C637719545203913471%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=Eb8Gp0X0k5%2B7%2B%2BKtguNKXvWaYq1k3Lekxvzu2W5FKGc%3D&reserved=0>
>>>
>>>
>>>
>>>
>>>
>>> *From:* Connectionists <connectionists-bounces at mailman.srv.cs.cmu.edu> *On
>>> Behalf Of *Adam Krawitz
>>> *Sent:* Friday, November 5, 2021 10:01 AM
>>> *To:* connectionists at cs.cmu.edu
>>> *Subject:* Re: Connectionists: Scientific Integrity, the 2021 Turing
>>> Lecture, etc.
>>>
>>>
>>>
>>> Tsvi,
>>>
>>>
>>>
>>> I’m just a lurker on this list, with no skin in the game, but perhaps
>>> that gives me a more neutral perspective. In the spirit of progress:
>>>
>>>
>>>
>>> 1. If you have a neural network approach that you feel provides a
>>> new and important perspective on cognitive processes, then write up a paper
>>> making that argument clearly, and I think you will find that the community
>>> is incredibly open to that. Yes, if they see holes in the approach they
>>> will be pointed out, but that is all part of the scientific exchange.
>>> Examples of this approach include: Elman (1990) Finding Structure in Time,
>>> Kohonen (1990) The Self-Organizing Map, Tenenbaum et al. (2011) How to Grow
>>> a Mind: Statistics, Structure, and Abstraction (not neural nets, but a
>>> “new” approach to modelling cognition). I’m sure others can provide more
>>> examples.
>>> 2. I’m much less familiar with how things work on the applied side,
>>> but I have trouble believing that Google or anyone else will be dismissive
>>> of a computational approach that actually works. Why would they? They just
>>> want to solve problems efficiently. Demonstrate that your approach can
>>> solve a problem more effectively (or at least as effectively) as the
>>> existing approaches, and they will come running. Examples of this include:
>>> Tesauro’s TD-Gammon, which was influential in demonstrating the power of
>>> RL, and LeCun et al.’s convolutional NN for the MNIST digits.
>>>
>>>
>>>
>>> Clearly communicate the novel contribution of your approach and I think
>>> you will find a receptive audience.
>>>
>>>
>>>
>>> Thanks,
>>>
>>> Adam
>>>
>>>
>>>
>>>
>>>
>>> *From:* Connectionists <connectionists-bounces at mailman.srv.cs.cmu.edu> *On
>>> Behalf Of *Tsvi Achler
>>> *Sent:* November 4, 2021 9:46 AM
>>> *To:* gary at ucsd.edu
>>> *Cc:* connectionists at cs.cmu.edu
>>> *Subject:* Re: Connectionists: Scientific Integrity, the 2021 Turing
>>> Lecture, etc.
>>>
>>>
>>>
>>> Lastly Feedforward methods are predominant in a large part because they
>>> have financial backing from large companies with advertising and clout like
>>> Google and the self-driving craze that never fully materialized.
>>>
>>>
>>>
>>> Feedforward methods are not fully connectionist unless rehearsal for
>>> learning is implemented with neurons. That means storing all patterns,
>>> mixing them randomly and then presenting to a network to learn. As far as
>>> I know, no one is doing this in the community, so feedforward methods are
>>> only partially connectionist. By allowing popularity to predominate and
>>> choking off funds and presentation of alternatives we are cheating
>>> ourselves from pursuing other more rigorous brain-like methods.
>>>
>>>
>>>
>>> Sincerely,
>>>
>>> -Tsvi
>>>
>>>
>>>
>>>
>>>
>>> On Tue, Nov 2, 2021 at 7:08 PM Tsvi Achler <achler at gmail.com> wrote:
>>>
>>> Gary- Thanks for the accessible online link to the book.
>>>
>>>
>>>
>>> I looked especially at the inhibitory feedback section of the book which
>>> describes an Air Conditioner AC type feedback.
>>>
>>> It then describes a general field-like inhibition based on all
>>> activations in the layer. It also describes the role of inhibition in
>>> sparsity and feedforward inhibition,
>>>
>>>
>>>
>>> The feedback described in Regulatory Feedback is similar to the AC
>>> feedback but occurs for each neuron individually, vis-a-vis its inputs.
>>>
>>> Thus for context, regulatory feedback is not a field-like inhibition, it
>>> is very directed based on the neurons that are activated and their inputs.
>>> This sort of regulation is also the foundation of Homeostatic Plasticity
>>> findings (albeit with changes in Homeostatic regulation in experiments
>>> occurring in a slower time scale). The regulatory feedback model describes
>>> the effect and role in recognition of those regulated connections in real
>>> time during recognition.
>>>
>>>
>>>
>>> I would be happy to discuss further and collaborate on writing about the
>>> differences between the approaches for the next book or review.
>>>
>>>
>>>
>>> And I want to point out to folks, that the system is based on politics
>>> and that is why certain work is not cited like it should, but even worse
>>> these politics are here in the group today and they continue to very
>>> strongly influence decisions in the connectionist community and holds us
>>> back.
>>>
>>>
>>>
>>> Sincerely,
>>>
>>> -Tsvi
>>>
>>>
>>>
>>> On Mon, Nov 1, 2021 at 10:59 AM gary at ucsd.edu <gary at eng.ucsd.edu> wrote:
>>>
>>> Tsvi - While I think Randy and Yuko's book
>>> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com%2Fv3%2F__https%3A%2Fwww.amazon.com%2Fdp%2F0262650541%2F__%3B!!IKRxdwAv5BmarQ!P43fgF97h1EkMmUyqwIyGb3BiM6QvDDIayyZy_zt_11O7NVqPb6YiU7U4snDyk0%24&data=04%7C01%7Cminaiaa%40ucmail.uc.edu%7Cfb6eeb2f02f04eb8ba0808d9a28c2aad%7Cf5222e6c5fc648eb8f0373db18203b63%7C1%7C0%7C637719545203923458%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=WzBcZET%2FhYQ699dS4q6fT%2BHxu11Rr5maCF9%2BqWVeiXY%3D&reserved=0>is
>>> actually somewhat better than the online version (and buying choices on
>>> amazon start at $9.99), there *is* an online version.
>>> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com%2Fv3%2F__https%3A%2Fcompcogneuro.org%2F__%3B!!IKRxdwAv5BmarQ!P43fgF97h1EkMmUyqwIyGb3BiM6QvDDIayyZy_zt_11O7NVqPb6YiU7UH2qn4go%24&data=04%7C01%7Cminaiaa%40ucmail.uc.edu%7Cfb6eeb2f02f04eb8ba0808d9a28c2aad%7Cf5222e6c5fc648eb8f0373db18203b63%7C1%7C0%7C637719545203923458%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=KZ7%2BxRAdUGHC39R8hZpehaahxgzpQ6PmJ8cQSQmcBjQ%3D&reserved=0>
>>>
>>>
>>> Randy & Yuko's models take into account feedback and inhibition.
>>>
>>>
>>>
>>> On Mon, Nov 1, 2021 at 10:05 AM Tsvi Achler <achler at gmail.com> wrote:
>>>
>>> Daniel,
>>>
>>>
>>>
>>> Does your book include a discussion of Regulatory or Inhibitory Feedback
>>> published in several low impact journals between 2008 and 2014 (and in
>>> videos subsequently)?
>>>
>>> These are networks where the primary computation is inhibition back to
>>> the inputs that activated them and may be very counterintuitive given
>>> today's trends. You can almost think of them as the opposite of Hopfield
>>> networks.
>>>
>>>
>>>
>>> I would love to check inside the book but I dont have an academic budget
>>> that allows me access to it and that is a huge part of the problem with how
>>> information is shared and funding is allocated. I could not get access to
>>> any of the text or citations especially Chapter 4: "Competition, Lateral
>>> Inhibition, and Short-Term Memory", to weigh in.
>>>
>>>
>>>
>>> I wish the best circulation for your book, but even if the Regulatory
>>> Feedback Model is in the book, that does not change the fundamental problem
>>> if the book is not readily available.
>>>
>>>
>>>
>>> The same goes with Steve Grossberg's book, I cannot easily look inside.
>>> With regards to Adaptive Resonance I dont subscribe to lateral inhibition
>>> as a predominant mechanism, but I do believe a function such as vigilance
>>> is very important during recognition and Adaptive Resonance is one of
>>> a very few models that have it. The Regulatory Feedback model I have
>>> developed (and Michael Spratling studies a similar model as well) is built
>>> primarily using the vigilance type of connections and allows multiple
>>> neurons to be evaluated at the same time and continuously during
>>> recognition in order to determine which (single or multiple neurons
>>> together) match the inputs the best without lateral inhibition.
>>>
>>>
>>>
>>> Unfortunately within conferences and talks predominated by the Adaptive
>>> Resonance crowd I have experienced the familiar dismissiveness and did not
>>> have an opportunity to give a proper talk. This goes back to the larger
>>> issue of academic politics based on small self-selected committees, the
>>> same issues that exist with the feedforward crowd, and pretty much all of
>>> academia.
>>>
>>>
>>>
>>> Today's information age algorithms such as Google's can determine
>>> relevance of information and ways to display them, but hegemony of the
>>> journal systems and the small committee system of academia developed in the
>>> middle ages (and their mutual synergies) block the use of more modern
>>> methods in research. Thus we are stuck with this problem, which especially
>>> affects those that are trying to introduce something new and
>>> counterintuitive, and hence the results described in the two National
>>> Bureau of Economic Research articles I cited in my previous message.
>>>
>>>
>>>
>>> Thomas, I am happy to have more discussions and/or start a different
>>> thread.
>>>
>>>
>>>
>>> Sincerely,
>>>
>>> Tsvi Achler MD/PhD
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>> On Sun, Oct 31, 2021 at 12:49 PM Levine, Daniel S <levine at uta.edu>
>>> wrote:
>>>
>>> Tsvi,
>>>
>>>
>>>
>>> While deep learning and feedforward networks have an outsize popularity,
>>> there are plenty of published sources that cover a much wider variety of
>>> networks, many of them more biologically based than deep learning. A
>>> treatment of a range of neural network approaches, going from simpler to
>>> more complex cognitive functions, is found in my textbook *Introduction
>>> to Neural and Cognitive Modeling* (3rd edition, Routledge, 2019). Also
>>> Steve Grossberg's book *Conscious Mind, Resonant Brain* (Oxford, 2021)
>>> emphasizes a variety of architectures with a strong biological basis.
>>>
>>>
>>>
>>>
>>>
>>> Best,
>>>
>>>
>>>
>>>
>>>
>>> Dan Levine
>>> ------------------------------
>>>
>>> *From:* Connectionists <connectionists-bounces at mailman.srv.cs.cmu.edu>
>>> on behalf of Tsvi Achler <achler at gmail.com>
>>> *Sent:* Saturday, October 30, 2021 3:13 AM
>>> *To:* Schmidhuber Juergen <juergen at idsia.ch>
>>> *Cc:* connectionists at cs.cmu.edu <connectionists at cs.cmu.edu>
>>> *Subject:* Re: Connectionists: Scientific Integrity, the 2021 Turing
>>> Lecture, etc.
>>>
>>>
>>>
>>> Since the title of the thread is Scientific Integrity, I want to point
>>> out some issues about trends in academia and then especially focusing on
>>> the connectionist community.
>>>
>>>
>>>
>>> In general analyzing impact factors etc the most important progress gets
>>> silenced until the mainstream picks it up Impact Factiors in novel
>>> research www.nber.org/.../working_papers/w22180/w22180.pdf
>>> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com%2Fv3%2F__https%3A%2Fnam12.safelinks.protection.outlook.com%2F%3Furl%3Dhttps*3A*2F*2Fwww.nber.org*2Fsystem*2Ffiles*2Fworking_papers*2Fw22180*2Fw22180.pdf*3Ffbclid*3DIwAR1zHhU4wmkrHASTaE-6zwIs6gI9-FxZcCED3BETxUJlMsbN_2hNbmJAmOA%26data%3D04*7C01*7Clevine*40uta.edu*7Cb1a267e3b6a64ada666208d99ca37f6d*7C5cdc5b43d7be4caa8173729e3b0a62d9*7C1*7C0*7C637713048300122043*7CUnknown*7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0*3D*7C1000%26sdata%3D9o*2FzcYY8gZVZiAwyEL5SVI9TEzBWfKf7nfhdWWg8LHU*3D%26reserved%3D0__%3BJSUlJSUlJSUlJSUlJSUlJSUlJSUlJSUl!!IKRxdwAv5BmarQ!P43fgF97h1EkMmUyqwIyGb3BiM6QvDDIayyZy_zt_11O7NVqPb6YiU7UD9hRGNg%24&data=04%7C01%7Cminaiaa%40ucmail.uc.edu%7Cfb6eeb2f02f04eb8ba0808d9a28c2aad%7Cf5222e6c5fc648eb8f0373db18203b63%7C1%7C0%7C637719545203933455%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=VQU9bWmSvIlc7xhOtjEydGMEMSC1fxhbatt%2BMNvYbG0%3D&reserved=0> and
>>> often this may take a generation
>>> https://www.nber.org/.../does-science-advance-one-funeral...
>>> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com%2Fv3%2F__https%3A%2Fnam12.safelinks.protection.outlook.com%2F%3Furl%3Dhttps*3A*2F*2Fwww.nber.org*2Fdigest*2Fmar16*2Fdoes-science-advance-one-funeral-time*3Ffbclid*3DIwAR1Lodsf1bzje-yQU9DvoZE2__S6R7UPEgY1_LxZCSLdoAYnj-uco0JuyVk%26data%3D04*7C01*7Clevine*40uta.edu*7Cb1a267e3b6a64ada666208d99ca37f6d*7C5cdc5b43d7be4caa8173729e3b0a62d9*7C1*7C0*7C637713048300132034*7CUnknown*7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0*3D*7C1000%26sdata%3DDgxnJTT7MsN5KCzZlA7VAHKrHXVsRsYhopJv0FCwbtw*3D%26reserved%3D0__%3BJSUlJSUlJSUlJSUlJSUlJSUlJSUl!!IKRxdwAv5BmarQ!P43fgF97h1EkMmUyqwIyGb3BiM6QvDDIayyZy_zt_11O7NVqPb6YiU7UapVS1t0%24&data=04%7C01%7Cminaiaa%40ucmail.uc.edu%7Cfb6eeb2f02f04eb8ba0808d9a28c2aad%7Cf5222e6c5fc648eb8f0373db18203b63%7C1%7C0%7C637719545203943446%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=9%2FevVDK3HbzdVf2LY26FLauA8%2B8vFAQ4Dj4fYD2YepM%3D&reserved=0>
>>> .
>>>
>>>
>>>
>>> The connectionist field is stuck on feedforward networks and variants
>>> such as with inhibition of competitors (e.g. lateral inhibition), or other
>>> variants that are sometimes labeled as recurrent networks for learning time
>>> where the feedforward networks can be rewound in time.
>>>
>>>
>>>
>>> This stasis is specifically occuring with the popularity of deep
>>> learning. This is often portrayed as neurally plausible connectionism but
>>> requires an implausible amount of rehearsal and is not connectionist if
>>> this rehearsal is not implemented with neurons (see video link for further
>>> clarification).
>>>
>>>
>>>
>>> Models which have true feedback (e.g. back to their own inputs) cannot
>>> learn by backpropagation but there is plenty of evidence these types of
>>> connections exist in the brain and are used during recognition. Thus they
>>> get ignored: no talks in universities, no featuring in "premier" journals
>>> and no funding.
>>>
>>>
>>>
>>> But they are important and may negate the need for rehearsal as needed
>>> in feedforward methods. Thus may be essential for moving connectionism
>>> forward.
>>>
>>>
>>>
>>> If the community is truly dedicated to brain motivated algorithms, I
>>> recommend giving more time to networks other than feedforward networks.
>>>
>>>
>>>
>>> Video:
>>> https://www.youtube.com/watch?v=m2qee6j5eew&list=PL4nMP8F3B7bg3cNWWwLG8BX-wER2PeB-3&index=2
>>> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com%2Fv3%2F__https%3A%2Fnam12.safelinks.protection.outlook.com%2F%3Furl%3Dhttps*3A*2F*2Fwww.youtube.com*2Fwatch*3Fv*3Dm2qee6j5eew*26list*3DPL4nMP8F3B7bg3cNWWwLG8BX-wER2PeB-3*26index*3D2%26data%3D04*7C01*7Clevine*40uta.edu*7Cb1a267e3b6a64ada666208d99ca37f6d*7C5cdc5b43d7be4caa8173729e3b0a62d9*7C1*7C0*7C637713048300132034*7CUnknown*7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0*3D*7C1000%26sdata%3DEaEp5zLZ7HkDhsBHmP3x3ObPl8j14B8*2BFcOkkNEWZ9w*3D%26reserved%3D0__%3BJSUlJSUlJSUlJSUlJSUlJSUlJSUlJSUl!!IKRxdwAv5BmarQ!P43fgF97h1EkMmUyqwIyGb3BiM6QvDDIayyZy_zt_11O7NVqPb6YiU7UzMnNL04%24&data=04%7C01%7Cminaiaa%40ucmail.uc.edu%7Cfb6eeb2f02f04eb8ba0808d9a28c2aad%7Cf5222e6c5fc648eb8f0373db18203b63%7C1%7C0%7C637719545203943446%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=wshBwOlWkcj7kxXFnQmOkMmfF1oqT39TeGgaWau%2FMPQ%3D&reserved=0>
>>>
>>>
>>>
>>> Sincerely,
>>>
>>> Tsvi Achler
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>> On Wed, Oct 27, 2021 at 2:24 AM Schmidhuber Juergen <juergen at idsia.ch>
>>> wrote:
>>>
>>> Hi, fellow artificial neural network enthusiasts!
>>>
>>> The connectionists mailing list is perhaps the oldest mailing list on
>>> ANNs, and many neural net pioneers are still subscribed to it. I am hoping
>>> that some of them - as well as their contemporaries - might be able to
>>> provide additional valuable insights into the history of the field.
>>>
>>> Following the great success of massive open online peer review (MOOR)
>>> for my 2015 survey of deep learning (now the most cited article ever
>>> published in the journal Neural Networks), I've decided to put forward
>>> another piece for MOOR. I want to thank the many experts who have already
>>> provided me with comments on it. Please send additional relevant references
>>> and suggestions for improvements for the following draft directly to me at
>>> juergen at idsia.ch:
>>>
>>>
>>> https://people.idsia.ch/~juergen/scientific-integrity-turing-award-deep-learning.html
>>> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com%2Fv3%2F__https%3A%2Fnam12.safelinks.protection.outlook.com%2F%3Furl%3Dhttps*3A*2F*2Fpeople.idsia.ch*2F*juergen*2Fscientific-integrity-turing-award-deep-learning.html%26data%3D04*7C01*7Clevine*40uta.edu*7Cb1a267e3b6a64ada666208d99ca37f6d*7C5cdc5b43d7be4caa8173729e3b0a62d9*7C1*7C0*7C637713048300142030*7CUnknown*7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0*3D*7C1000%26sdata%3DmW3lH7SqKg4EuJfDwKcC2VhwEloC3ndh6kI5gfQ2Ofw*3D%26reserved%3D0__%3BJSUlJX4lJSUlJSUlJSUlJSUlJQ!!IKRxdwAv5BmarQ!P43fgF97h1EkMmUyqwIyGb3BiM6QvDDIayyZy_zt_11O7NVqPb6YiU7UNznV_Qo%24&data=04%7C01%7Cminaiaa%40ucmail.uc.edu%7Cfb6eeb2f02f04eb8ba0808d9a28c2aad%7Cf5222e6c5fc648eb8f0373db18203b63%7C1%7C0%7C637719545203953444%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=J%2Fcu7KnaRG2%2FaIDlhtQ7IrO3D8nymFzrO6%2FMRT8A2RY%3D&reserved=0>
>>>
>>> The above is a point-for-point critique of factual errors in ACM's
>>> justification of the ACM A. M. Turing Award for deep learning and a
>>> critique of the Turing Lecture published by ACM in July 2021. This work can
>>> also be seen as a short history of deep learning, at least as far as ACM's
>>> errors and the Turing Lecture are concerned.
>>>
>>> I know that some view this as a controversial topic. However, it is the
>>> very nature of science to resolve controversies through facts. Credit
>>> assignment is as core to scientific history as it is to machine learning.
>>> My aim is to ensure that the true history of our field is preserved for
>>> posterity.
>>>
>>> Thank you all in advance for your help!
>>>
>>> Jürgen Schmidhuber
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>> --
>>>
>>> Gary Cottrell 858-534-6640 FAX: 858-534-7029
>>>
>>> Computer Science and Engineering 0404
>>> IF USING FEDEX INCLUDE THE FOLLOWING LINE:
>>> CSE Building, Room 4130
>>> University of California San Diego -
>>> 9500 Gilman Drive # 0404
>>> La Jolla, Ca. 92093-0404
>>>
>>> Email: gary at ucsd.edu
>>> Home page: http://www-cse.ucsd.edu/~gary/
>>> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com%2Fv3%2F__http%3A%2Fwww-cse.ucsd.edu%2F*gary%2F__%3Bfg!!IKRxdwAv5BmarQ!P43fgF97h1EkMmUyqwIyGb3BiM6QvDDIayyZy_zt_11O7NVqPb6YiU7U-G68mLE%24&data=04%7C01%7Cminaiaa%40ucmail.uc.edu%7Cfb6eeb2f02f04eb8ba0808d9a28c2aad%7Cf5222e6c5fc648eb8f0373db18203b63%7C1%7C0%7C637719545203963435%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=ZuIDqivh89yvJ4syDWTsXtIDrnd3ry1hI890%2FSLitFw%3D&reserved=0>
>>>
>>> Schedule: http://tinyurl.com/b7gxpwo
>>> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com%2Fv3%2F__http%3A%2Ftinyurl.com%2Fb7gxpwo__%3B!!IKRxdwAv5BmarQ!P43fgF97h1EkMmUyqwIyGb3BiM6QvDDIayyZy_zt_11O7NVqPb6YiU7UcMz40H8%24&data=04%7C01%7Cminaiaa%40ucmail.uc.edu%7Cfb6eeb2f02f04eb8ba0808d9a28c2aad%7Cf5222e6c5fc648eb8f0373db18203b63%7C1%7C0%7C637719545203973431%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=%2BxsOrKBZFCCkQZ%2FgRdkrZ5BizkQaMnsnBkE%2Bqfms4HA%3D&reserved=0>
>>>
>>>
>>>
>>> *Listen carefully,*
>>> *Neither the Vedas*
>>> *Nor the Qur'an*
>>> *Will teach you this:*
>>> *Put the bit in its mouth,*
>>> *The saddle on its back,*
>>> *Your foot in the stirrup,*
>>> *And ride your wild runaway mind*
>>> *All the way to heaven.*
>>>
>>> *-- Kabir*
>>>
>>>
>
> --
> Juyang (John) Weng
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20211110/0ec140fc/attachment.html>
More information about the Connectionists
mailing list