Connectionists: Stephen Hanson in conversation with Geoff Hinton

[Danko Nikolic]

Hi Gary,

Thank you for inquiring about the generalized XOR? To answer such question,
I wrote a paper. So, please read the paper. Everything should be explained
over there better than what I can do in a short message (there are
additional details in the supplementary materials; also the code on github).

In short, learning mechanisms cannot discover generalized XOR functions
with simple connectivity -- only with complex connectivity. This problem
results in exponential growth of needed resources as the number of bits in
the generalized XOR increases.

Remember, we are talking about a generalized XOR (more than two bits as
inputs).

The paper: https://bit.ly/3IFs8Ug
<https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fbit.ly%2F3IFs8Ug&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=dMSUKAQT%2FdnZEgC8Hc1t2Ggn0QMpkzUlnANbO8KXq%2FI%3D&reserved=0>

As you will see, although connectionism can scale linearly in theory, in
practice no learning mechanism seems to exist that could discover the
needed connections. This would require super-smart learning mechanisms, but
such mechanisms do not exist. As a result, the whole thing fails.

And, as I mentioned before, even the linear scaling would not be enough to
match the biological brain. We need something a lot more powerful than
linear scaling. This is my argument on why connectionism fails; it
fails even with linear scaling, which it cannot achieve anyway in practice.
Again, these are not just empty works; I provide evidence for that in the
manuscript.

The good news is that there seems to be a solution: transient selection of
subnetworks, which I characterize in the same paper. So, the future of AI
looks nevertheless bright, I think.

Danko

Dr. Danko Nikolić
www.danko-nikolic.com
https://www.linkedin.com/in/danko-nikolic/
-- I wonder, how is the brain able to generate insight? --


On Mon, Jul 18, 2022 at 12:59 AM gary at ucsd.edu <gary at eng.ucsd.edu> wrote:

> Sorry, I can't let this go by:
>
> And it is good so because generalize XOR scales worse than power law. It
> scales exponentially! This a more agressive form of explosion than power
> law.
>
> I'm not sure exactly what you mean by this, but a single-hidden layer
> network with N inputs and N hidden units can solve N-bit parity. Each unit
> has an increasing threshold, so, one turns on if there is one unit on in
> the input, and then turns on the output with a weight of +1. If two units
> are on in the input, then a second unit comes on and cancels the activation
> of the first unit via a weight of -1. Etc.
>
> g.
>
>
> On Sat, Jul 16, 2022 at 12:03 AM Danko Nikolic <danko.nikolic at gmail.com>
> wrote:
>
>> Dear Thomas,
>>
>> Thank you for reading the paper and for the comments.
>>
>> I cite: "In my experience, supervised classification scales linearly in
>> the number of classes."
>> This would be good to quantify as a plot. Maybe a research paper would be
>> a good idea. The reason is that it seems that everyone else who tried to
>> quantify that relation found a power law. At this point, it would be
>> surprising to find a linear relationship. And it would probably make a well
>> read paper.
>>
>> But please do not forget that my argument states that even a linear
>> relationship is not good enough to match bilogical brains. We need
>> something more similar to a power law with exponent zero when it comes to
>> the model size i.e., a constant number of parameters in the model. And we
>> need linear relationship when it comes to learning time: Each newly learned
>> object should needs about as much of learning effort as was needed for each
>> previous object.
>>
>> I cite: "The real world is not dominated by generalized XOR problems."
>> Agreed. And it is good so because generalize XOR scales worse than power
>> law. It scales exponentially! This a more agressive form of explosion than
>> power law.
>> Importantly, a generalized AND operation also scales exponentially (with
>> a smaller exponent, though). I guess we would agree that the real world
>> probably encouners a lot of AND problems. The only logical operaiton that
>> could be learned with a linear increase in the number of parameters was a
>> generalized OR. Finally, I foiund that a mixure of AND and OR resulted in a
>> power law-like scaling of the number of parameters. So, a mixture of AND
>> and OR seemed to scale as good (or as bad) as the real world. I have put
>> this information into Supplementary Materials.
>>
>> The conclusion that I derived from those analyses is: connectionism is
>> not sustainable to reach human (or animal) levels of intelligence.
>> Therefore, I hunted for an alternative pradigm.
>>
>> Greetings,
>>
>> Danko
>>
>>
>>
>> Dr. Danko Nikolić
>> www.danko-nikolic.com
>> https://www.linkedin.com/in/danko-nikolic/
>> -- I wonder, how is the brain able to generate insight? --
>>
>>
>> On Fri, Jul 15, 2022 at 10:01 AM Dietterich, Thomas <tgd at oregonstate.edu>
>> wrote:
>>
>>> Dear Danko,
>>>
>>>
>>>
>>> In my experience, supervised classification scales linearly in the
>>> number of classes. Of course it depends to some extent on how subtle the
>>> distinctions are between the different categories. The real world is not
>>> dominated by generalized XOR problems.
>>>
>>>
>>>
>>> --Tom
>>>
>>>
>>>
>>> Thomas G. Dietterich, Distinguished Professor Voice: 541-737-5559
>>>
>>> School of Electrical Engineering              FAX: 541-737-1300
>>>
>>>   and Computer Science                        URL:
>>> eecs.oregonstate.edu/~tgd
>>>
>>> US Mail: 1148 Kelley Engineering Center
>>>
>>> Office: 2067 Kelley Engineering Center
>>>
>>> Oregon State Univ., Corvallis, OR 97331-5501
>>>
>>>
>>>
>>> *From:* Connectionists <connectionists-bounces at mailman.srv.cs.cmu.edu> *On
>>> Behalf Of *Danko Nikolic
>>> *Sent:* Thursday, July 14, 2022 09:17
>>> *To:* Grossberg, Stephen <steve at bu.edu>
>>> *Cc:* AIhub <aihuborg at gmail.com>; connectionists at mailman.srv.cs.cmu.edu
>>> *Subject:* Re: Connectionists: Stephen Hanson in conversation with
>>> Geoff Hinton
>>>
>>>
>>>
>>> [This email originated from outside of OSU. Use caution with links and
>>> attachments.]
>>>
>>> Dear Steve,
>>>
>>>
>>>
>>> Thank you very much for your message and for the greetings. I will pass
>>> them on if an occasion arises.
>>>
>>>
>>>
>>> Regarding your question: The key problem I am trying to address and
>>> that, to the best of my knowledge, no connectionist system was able to
>>> solve so far is that of scaling the system's intelligence. For example, if
>>> the system is able to correctly recognize 100 different objects, how many
>>> additional resources are needed to double that to 200? All the empirical
>>> data show that connectionist systems scale poorly: Some of the best systems
>>> we have require 500x more resources in order to increase the intelligence
>>> by only 2x. I document this problem in the manuscript and even run some
>>> simulations to show that the worst performance is if connectionist systems
>>> need to solve a generalized XOR problem.
>>>
>>>
>>>
>>> In contrast, the biological brain scales well. This I also quantify in
>>> the paper.
>>>
>>>
>>>
>>> I will look at the publication that you mentioned. However, so far, I
>>> haven't seen a solution that scales well in intelligence.
>>>
>>>
>>>
>>> My argument is that transient selection of subnetworks by the help of
>>> the mentioned proteins is how intelligence scaling is achieved in
>>> biological brains.
>>>
>>>
>>>
>>> In short, intelligence scaling is the key problem that concerns me. I
>>> describe the intelligence scaling problem in more detail in this book that
>>> just came out a few weeks ago and that is written for practitioners in Data
>>> Scientist and AI: https://amzn.to/3IBxUpL
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Famzn.to%2F3IBxUpL&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009661467%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=Q7ZuNuMhL1M3WC7AKphyihjhsXCmI4gg2iZpv0n74zM%3D&reserved=0>
>>>
>>>
>>>
>>> I hope that this at least partly answers where I see the problems and
>>> what I am trying to solve.
>>>
>>>
>>>
>>> Greetings from Germany,
>>>
>>>
>>>
>>> Danko
>>>
>>>
>>> Dr. Danko Nikolić
>>> www.danko-nikolic.com
>>> <https://nam04.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.danko-nikolic.com%2F&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=QTR9i3jFBKmYC32qKigQ1WD4SyucpL9udIA4awPpU6E%3D&reserved=0>
>>> https://www.linkedin.com/in/danko-nikolic/
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.linkedin.com%2Fin%2Fdanko-nikolic%2F&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=DrZAreOWTk24TyQtQNT7YU%2Bhs3CnNdFKhVtbLvhiEaU%3D&reserved=0>
>>>
>>> --- A progress usually starts with an insight ---
>>>
>>>
>>>
>>>
>>>
>>> On Thu, Jul 14, 2022 at 3:30 PM Grossberg, Stephen <steve at bu.edu> wrote:
>>>
>>> Dear Danko,
>>>
>>>
>>>
>>> I have just read your new article and would like to comment briefly
>>> about it.
>>>
>>>
>>>
>>> In your introductory remarks, you write:
>>>
>>>
>>>
>>> "However, connectionism did not yet produce a satisfactory explanation
>>> of how the mental emerges from the physical. A number of open problems
>>> remains ( 5,6,7,8). As a result, the explanatory gap between the mind and
>>> the brain remains wide open."
>>>
>>>
>>>
>>> I certainly believe that no theoretical explanation in science is ever
>>> complete. However, I also believe that "the explanatory gap between the
>>> mind and the brain" does not remain "wide open".
>>>
>>>
>>>
>>> My Magnum Opus, that was published in 2021, makes that belief clear in
>>> its title:
>>>
>>>
>>>
>>> *Conscious Mind, Resonant Brain: How Each Brain Makes a Mind*
>>>
>>>
>>>
>>> https://www.amazon.com/Conscious-Mind-Resonant-Brain-Makes/dp/0190070552
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.amazon.com%2FConscious-Mind-Resonant-Brain-Makes%2Fdp%2F0190070552&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=6OJwAuUjVNXT3I4O7H1coUDuOA2cpFitVk37M43v2W8%3D&reserved=0>
>>>
>>>
>>>
>>> The book provides a self-contained and non-technical exposition in a
>>> conversational tone of many principled and unifying explanations of
>>> psychological and neurobiological data.
>>>
>>>
>>>
>>> In particular, it explains roles for the metabotropic glutamate
>>> receptors that you mention in your own work. See the text and figures
>>> around p. 521. This explanation unifies psychological, anatomical,
>>> neurophysiological, biophysical, and biochemical data about the processes
>>> under discussion.
>>>
>>>
>>>
>>> I have a very old-fashioned view about how to understand scientific
>>> theories. I get excited by theories that explain and predict more data than
>>> previous theories.
>>>
>>>
>>>
>>> Which of the data that I explain in my book, and support with
>>> quantitative computer simulations, can you also explain?
>>>
>>>
>>>
>>> What data can you explain, in the same quantitative sense, that you do
>>> not think the neural models in my book can explain?
>>>
>>>
>>>
>>> I would be delighted to discuss these issues further with you.
>>>
>>>
>>>
>>> If you are in touch with my old friend and esteemed colleague, Wolf
>>> Singer, please send him my warm regards. I cite the superb work that he and
>>> various of his collaborators have done in many places in my book.
>>>
>>>
>>>
>>> Best,
>>>
>>>
>>>
>>> Steve
>>>
>>>
>>>
>>> Stephen Grossberg
>>>
>>> http://en.wikipedia.org/wiki/Stephen_Grossberg
>>> <https://nam04.safelinks.protection.outlook.com/?url=http%3A%2F%2Fen.wikipedia.org%2Fwiki%2FStephen_Grossberg&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=SQVrXcpNHPkeU6zaBSfMTCGjs7LPI0xQW2Wf88Vyzp8%3D&reserved=0>
>>>
>>> http://scholar.google.com/citations?user=3BIV70wAAAAJ&hl=en
>>> <https://nam04.safelinks.protection.outlook.com/?url=http%3A%2F%2Fscholar.google.com%2Fcitations%3Fuser%3D3BIV70wAAAAJ%26hl%3Den&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=Tlb9uRaNugf0TKUCtg8gLmV8IaWpZiY3Bv1B6ex183I%3D&reserved=0>
>>>
>>> https://youtu.be/9n5AnvFur7I
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fyoutu.be%2F9n5AnvFur7I&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=HDSOTohhQK6wLL4wSfmyryfvLOF41MXs8sE%2BWX2c8Cs%3D&reserved=0>
>>>
>>> https://www.youtube.com/watch?v=_hBye6JQCh4
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3D_hBye6JQCh4&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=PqAFTvHU7CdwZ%2FKdoPy%2Faq0UxThxLIpCTgUqXXh4c%2Bk%3D&reserved=0>
>>>
>>> https://www.amazon.com/Conscious-Mind-Resonant-Brain-Makes/dp/0190070552
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.amazon.com%2FConscious-Mind-Resonant-Brain-Makes%2Fdp%2F0190070552&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=6OJwAuUjVNXT3I4O7H1coUDuOA2cpFitVk37M43v2W8%3D&reserved=0>
>>>
>>>
>>> Wang Professor of Cognitive and Neural Systems
>>>
>>> Director, Center for Adaptive Systems
>>> Professor Emeritus of Mathematics & Statistics,
>>>
>>>        Psychological & Brain Sciences, and Biomedical Engineering
>>>
>>> Boston University
>>> sites.bu.edu/steveg
>>> <https://nam04.safelinks.protection.outlook.com/?url=http%3A%2F%2Fsites.bu.edu%2Fsteveg&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=nmfU9sc%2FeYZldTeJRFzBnjpxqeDOaKSv%2FEn6mKCrODo%3D&reserved=0>
>>> steve at bu.edu
>>>
>>>
>>> ------------------------------
>>>
>>> *From:* Connectionists <connectionists-bounces at mailman.srv.cs.cmu.edu>
>>> on behalf of Danko Nikolic <danko.nikolic at gmail.com>
>>> *Sent:* Thursday, July 14, 2022 6:05 AM
>>> *To:* Gary Marcus <gary.marcus at nyu.edu>
>>> *Cc:* connectionists at mailman.srv.cs.cmu.edu <
>>> connectionists at mailman.srv.cs.cmu.edu>; AIhub <aihuborg at gmail.com>
>>> *Subject:* Re: Connectionists: Stephen Hanson in conversation with
>>> Geoff Hinton
>>>
>>>
>>>
>>> Dear Gary and everyone,
>>>
>>>
>>>
>>> I am continuing the discussion from where we left off a few months ago.
>>> Back then, some of us agreed that the problem of understanding remains
>>> unsolved.
>>>
>>>
>>>
>>> As a reminder, the challenge for connectionism was to 1) learn with few
>>> examples and 2) apply the knowledge to a broad set of situations.
>>>
>>>
>>>
>>> I am happy to announce that I have now finished a draft of a paper in
>>> which I propose how the brain is able to achieve that. The manuscript
>>> requires a bit of patience for two reasons: one is that the reader may be
>>> exposed for the first time to certain aspects of brain physiology. The
>>> second reason is that it may take some effort to understand the
>>> counterintuitive implications of the new ideas (this requires a different
>>> way of thinking than what we are used to based on connectionism).
>>>
>>>
>>>
>>> In short, I am suggesting that instead of the connectionist paradigm, we
>>> adopt transient selection of subnetworks. The mechanisms that transiently
>>> select brain subnetworks are distributed all over the nervous system and, I
>>> argue, are our main machinery for thinking/cognition. The surprising
>>> outcome is that neural activation, which was central in connectionism, now
>>> plays only a supportive role, while the real 'workers' within the brain are
>>> the mechanisms for transient selection of subnetworks.
>>>
>>>
>>>
>>> I also explain how I think transient selection achieves learning with
>>> only a few examples and how the learned knowledge is possible to apply to a
>>> broad set of situations.
>>>
>>>
>>>
>>> The manuscript is made available to everyone and can be downloaded here:
>>> https://bit.ly/3IFs8Ug
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fbit.ly%2F3IFs8Ug&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=dMSUKAQT%2FdnZEgC8Hc1t2Ggn0QMpkzUlnANbO8KXq%2FI%3D&reserved=0>
>>>
>>> (I apologize for the neuroscience lingo, which I tried to minimize.)
>>>
>>>
>>>
>>> It will likely take a wide effort to implement these concepts as an AI
>>> technology, provided my ideas do not have a major flaw in the first place.
>>> Does anyone see a flaw?
>>>
>>>
>>>
>>> Thanks.
>>>
>>>
>>>
>>> Danko
>>>
>>>
>>>
>>>
>>> Dr. Danko Nikolić
>>> www.danko-nikolic.com
>>> <https://nam04.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.danko-nikolic.com%2F&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=QTR9i3jFBKmYC32qKigQ1WD4SyucpL9udIA4awPpU6E%3D&reserved=0>
>>> https://www.linkedin.com/in/danko-nikolic/
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.linkedin.com%2Fin%2Fdanko-nikolic%2F&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=DrZAreOWTk24TyQtQNT7YU%2Bhs3CnNdFKhVtbLvhiEaU%3D&reserved=0>
>>>
>>>
>>>
>>>
>>>
>>> On Thu, Feb 3, 2022 at 5:25 PM Gary Marcus <gary.marcus at nyu.edu> wrote:
>>>
>>> Dear Danko,
>>>
>>>
>>>
>>> Well said. I had a somewhat similar response to Jeff Dean’s 2021 TED
>>> talk, in which he said (paraphrasing from memory, because I don’t remember
>>> the precise words) that the famous 200 Quoc Le unsupervised model [
>>> https://static.googleusercontent.com/media/research.google.com/en//archive/unsupervised_icml2012.pdf
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fstatic.googleusercontent.com%2Fmedia%2Fresearch.google.com%2Fen%2F%2Farchive%2Funsupervised_icml2012.pdf&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=T9m69LjMFTLkcipHgNFxYMKqVL8kUmFLkK3%2BmITrlRY%3D&reserved=0>]
>>> had learned the concept of a ca. In reality the model had clustered
>>> together some catlike images based on the image statistics that it had
>>> extracted, but it was a long way from a full, counterfactual-supporting
>>> concept of a cat, much as you describe below.
>>>
>>>
>>>
>>> I fully agree with you that the reason for even having a semantics is as
>>> you put it, "to 1) learn with a few examples and 2) apply the knowledge to
>>> a broad set of situations.” GPT-3 sometimes gives the appearance of having
>>> done so, but it falls apart under close inspection, so the problem remains
>>> unsolved.
>>>
>>>
>>>
>>> Gary
>>>
>>>
>>>
>>> On Feb 3, 2022, at 3:19 AM, Danko Nikolic <danko.nikolic at gmail.com>
>>> wrote:
>>>
>>>
>>>
>>> G. Hinton wrote: "I believe that any reasonable person would admit that
>>> if you ask a neural net to draw a picture of a hamster wearing a red hat
>>> and it draws such a picture, it understood the request."
>>>
>>>
>>>
>>> I would like to suggest why drawing a hamster with a red hat does not
>>> necessarily imply understanding of the statement "hamster wearing a red
>>> hat".
>>>
>>> To understand that "hamster wearing a red hat" would mean inferring, in
>>> newly emerging situations of this hamster, all the real-life
>>> implications that the red hat brings to the little animal.
>>>
>>>
>>>
>>> What would happen to the hat if the hamster rolls on its back? (Would
>>> the hat fall off?)
>>>
>>> What would happen to the red hat when the hamster enters its lair?
>>> (Would the hat fall off?)
>>>
>>> What would happen to that hamster when it goes foraging? (Would the red
>>> hat have an influence on finding food?)
>>>
>>> What would happen in a situation of being chased by a predator? (Would
>>> it be easier for predators to spot the hamster?)
>>>
>>>
>>>
>>> ...and so on.
>>>
>>>
>>>
>>> Countless many questions can be asked. One has understood "hamster
>>> wearing a red hat" only if one can answer reasonably well many of such
>>> real-life relevant questions. Similarly, a student has understood materias
>>> in a class only if they can apply the materials in real-life situations
>>> (e.g., applying Pythagora's theorem). If a student gives a correct answer
>>> to a multiple choice question, we don't know whether the student understood
>>> the material or whether this was just rote learning (often, it is rote
>>> learning).
>>>
>>>
>>>
>>> I also suggest that understanding also comes together with effective
>>> learning: We store new information in such a way that we can recall it
>>> later and use it effectively  i.e., make good inferences in newly emerging
>>> situations based on this knowledge.
>>>
>>>
>>>
>>> In short: Understanding makes us humans able to 1) learn with a few
>>> examples and 2) apply the knowledge to a broad set of situations.
>>>
>>>
>>>
>>> No neural network today has such capabilities and we don't know how to
>>> give them such capabilities. Neural networks need large amounts of
>>> training examples that cover a large variety of situations and then
>>> the networks can only deal with what the training examples have already
>>> covered. Neural networks cannot extrapolate in that 'understanding' sense.
>>>
>>>
>>>
>>> I suggest that understanding truly extrapolates from a piece of
>>> knowledge. It is not about satisfying a task such as translation between
>>> languages or drawing hamsters with hats. It is how you got the capability
>>> to complete the task: Did you only have a few examples that covered
>>> something different but related and then you extrapolated from that
>>> knowledge? If yes, this is going in the direction of understanding. Have
>>> you seen countless examples and then interpolated among them? Then perhaps
>>> it is not understanding.
>>>
>>>
>>>
>>> So, for the case of drawing a hamster wearing a red hat, understanding
>>> perhaps would have taken place if the following happened before that:
>>>
>>>
>>>
>>> 1) first, the network learned about hamsters (not many examples)
>>>
>>> 2) after that the network learned about red hats (outside the context of
>>> hamsters and without many examples)
>>>
>>> 3) finally the network learned about drawing (outside of the context of
>>> hats and hamsters, not many examples)
>>>
>>>
>>>
>>> After that, the network is asked to draw a hamster with a red hat. If it
>>> does it successfully, maybe we have started cracking the problem of
>>> understanding.
>>>
>>>
>>>
>>> Note also that this requires the network to learn sequentially without
>>> exhibiting catastrophic forgetting of the previous knowledge, which is
>>> possibly also a consequence of human learning by understanding.
>>>
>>>
>>>
>>>
>>>
>>> Danko
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>> Dr. Danko Nikolić
>>> www.danko-nikolic.com
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttp-3A__www.danko-2Dnikolic.com%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3DwaSKY67JF57IZXg30ysFB_R7OG9zoQwFwxyps6FbTa1Zh5mttxRot_t4N7mn68Pj%26s%3DHwOLDw6UCRzU5-FPSceKjtpNm7C6sZQU5kuGAMVbPaI%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=Mo0hlYOaYWD9%2BIsBvL%2BjLuaEhybPIpli0LLC2ra0Ez4%3D&reserved=0>
>>> https://www.linkedin.com/in/danko-nikolic/
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__www.linkedin.com_in_danko-2Dnikolic_%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3DwaSKY67JF57IZXg30ysFB_R7OG9zoQwFwxyps6FbTa1Zh5mttxRot_t4N7mn68Pj%26s%3Db70c8lokmxM3Kz66OfMIM4pROgAhTJOAlp205vOmCQ8%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=plMn26o%2FGLT2dOunALAatlC%2By3mBqxZRnKviibm79AM%3D&reserved=0>
>>>
>>> --- A progress usually starts with an insight ---
>>>
>>>
>>>
>>>
>>>
>>>
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__www.avast.com_sig-2Demail-3Futm-5Fmedium-3Demail-26utm-5Fsource-3Dlink-26utm-5Fcampaign-3Dsig-2Demail-26utm-5Fcontent-3Dwebmail%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3DwaSKY67JF57IZXg30ysFB_R7OG9zoQwFwxyps6FbTa1Zh5mttxRot_t4N7mn68Pj%26s%3DAo9QQWtO62go0hx1tb3NU6xw2FNBadjj8q64-hl5Sx4%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=rsYgVVa2s3yCcmNbasl8kL8baEkp9SfIIhOTaA2sAMc%3D&reserved=0>
>>>
>>> Virus-free. www.avast.com
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__www.avast.com_sig-2Demail-3Futm-5Fmedium-3Demail-26utm-5Fsource-3Dlink-26utm-5Fcampaign-3Dsig-2Demail-26utm-5Fcontent-3Dwebmail%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3DwaSKY67JF57IZXg30ysFB_R7OG9zoQwFwxyps6FbTa1Zh5mttxRot_t4N7mn68Pj%26s%3DAo9QQWtO62go0hx1tb3NU6xw2FNBadjj8q64-hl5Sx4%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=rsYgVVa2s3yCcmNbasl8kL8baEkp9SfIIhOTaA2sAMc%3D&reserved=0>
>>>
>>>
>>>
>>> On Thu, Feb 3, 2022 at 9:55 AM Asim Roy <ASIM.ROY at asu.edu> wrote:
>>>
>>> Without getting into the specific dispute between Gary and Geoff, I
>>> think with approaches similar to GLOM, we are finally headed in the right
>>> direction. There’s plenty of neurophysiological evidence for single-cell
>>> abstractions and multisensory neurons in the brain, which one might claim
>>> correspond to symbols. And I think we can finally reconcile the decades old
>>> dispute between Symbolic AI and Connectionism.
>>>
>>>
>>>
>>> GARY: (Your GLOM, which as you know I praised publicly, is in many ways
>>> an effort to wind up with encodings that effectively serve as symbols in
>>> exactly that way, guaranteed to serve as consistent representations of
>>> specific concepts.)
>>>
>>> GARY: I have *never* called for dismissal of neural networks, but
>>> rather for some hybrid between the two (as you yourself contemplated in
>>> 1991); the point of the 2001 book was to characterize exactly where
>>> multilayer perceptrons succeeded and broke down, and where symbols could
>>> complement them.
>>>
>>>
>>>
>>> Asim Roy
>>>
>>> Professor, Information Systems
>>>
>>> Arizona State University
>>>
>>> Lifeboat Foundation Bios: Professor Asim Roy
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__lifeboat.com_ex_bios.asim.roy%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3DwaSKY67JF57IZXg30ysFB_R7OG9zoQwFwxyps6FbTa1Zh5mttxRot_t4N7mn68Pj%26s%3DoDRJmXX22O8NcfqyLjyu4Ajmt8pcHWquTxYjeWahfuw%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=1e%2BbRdXdK4JTiOuh12cuqbGvQWvVUFQ31oGr%2BFBd8II%3D&reserved=0>
>>>
>>> Asim Roy | iSearch (asu.edu)
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__isearch.asu.edu_profile_9973%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3DwaSKY67JF57IZXg30ysFB_R7OG9zoQwFwxyps6FbTa1Zh5mttxRot_t4N7mn68Pj%26s%3DjCesWT7oGgX76_y7PFh4cCIQ-Ife-esGblJyrBiDlro%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=iLsLr1EIsUp9PeNFzjXupsadcfkhcaNKyW4tlP%2FCEXc%3D&reserved=0>
>>>
>>>
>>>
>>>
>>>
>>> *From:* Connectionists <connectionists-bounces at mailman.srv.cs.cmu.edu> *On
>>> Behalf Of *Gary Marcus
>>> *Sent:* Wednesday, February 2, 2022 1:26 PM
>>> *To:* Geoffrey Hinton <geoffrey.hinton at gmail.com>
>>> *Cc:* AIhub <aihuborg at gmail.com>; connectionists at mailman.srv.cs.cmu.edu
>>> *Subject:* Re: Connectionists: Stephen Hanson in conversation with
>>> Geoff Hinton
>>>
>>>
>>>
>>> Dear Geoff, and interested others,
>>>
>>>
>>>
>>> What, for example, would you make of a system that often drew the
>>> red-hatted hamster you requested, and perhaps a fifth of the time gave you
>>> utter nonsense?  Or say one that you trained to create birds but sometimes
>>> output stuff like this:
>>>
>>>
>>>
>>> <image001.png>
>>>
>>>
>>>
>>> One could
>>>
>>>
>>>
>>> a. avert one’s eyes and deem the anomalous outputs irrelevant
>>>
>>> or
>>>
>>> b. wonder if it might be possible that sometimes the system gets the
>>> right answer for the wrong reasons (eg partial historical contingency), and
>>> wonder whether another approach might be indicated.
>>>
>>>
>>>
>>> Benchmarks are harder than they look; most of the field has come to
>>> recognize that. The Turing Test has turned out to be a lousy measure of
>>> intelligence, easily gamed. It has turned out empirically that the Winograd
>>> Schema Challenge did not measure common sense as well as Hector might have
>>> thought. (As it happens, I am a minor coauthor of a very recent review on
>>> this very topic: https://arxiv.org/abs/2201.02387
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com%2Fv3%2F__https%3A%2Farxiv.org%2Fabs%2F2201.02387__%3B!!IKRxdwAv5BmarQ!INA0AMmG3iD1B8MDtLfjWCwcBjxO-e-eM2Ci9KEO_XYOiIEgiywK-G_8j6L3bHA%24&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=mC6NKLJ5rZ35YnzB%2Fr1S4owSqBoJmKSq1JIE3qScrlA%3D&reserved=0>)
>>> But its conquest in no way means machines now have common sense; many
>>> people from many different perspectives recognize that (including, e.g.,
>>> Yann LeCun, who generally tends to be more aligned with you than with me).
>>>
>>>
>>>
>>> So: on the goalpost of the Winograd schema, I was wrong, and you can
>>> quote me; but what you said about me and machine translation remains your
>>> invention, and it is inexcusable that you simply ignored my 2019
>>> clarification. On the essential goal of trying to reach meaning and
>>> understanding, I remain unmoved; the problem remains unsolved.
>>>
>>>
>>>
>>> All of the problems LLMs have with coherence, reliability, truthfulness,
>>> misinformation, etc stand witness to that fact. (Their persistent inability
>>> to filter out toxic and insulting remarks stems from the same.) I am hardly
>>> the only person in the field to see that progress on any given benchmark
>>> does not inherently mean that the deep underlying problems have solved.
>>> You, yourself, in fact, have occasionally made that point.
>>>
>>>
>>>
>>> With respect to embeddings: Embeddings are very good for natural
>>> language *processing*; but NLP is not the same as NL*U* – when it comes
>>> to *understanding*, their worth is still an open question. Perhaps they
>>> will turn out to be necessary; they clearly aren’t sufficient. In their
>>> extreme, they might even collapse into being symbols, in the sense of
>>> uniquely identifiable encodings, akin to the ASCII code, in which a
>>> specific set of numbers stands for a specific word or concept. (Wouldn’t
>>> that be ironic?)
>>>
>>>
>>>
>>> (Your GLOM, which as you know I praised publicly, is in many ways an
>>> effort to wind up with encodings that effectively serve as symbols in
>>> exactly that way, guaranteed to serve as consistent representations of
>>> specific concepts.)
>>>
>>>
>>>
>>> Notably absent from your email is any kind of apology for
>>> misrepresenting my position. It’s fine to say that “many people thirty
>>> years ago once thought X” and another to say “Gary Marcus said X in 2015”,
>>> when I didn’t. I have consistently felt throughout our interactions that
>>> you have mistaken me for Zenon Pylyshyn; indeed, you once (at NeurIPS 2014)
>>> apologized to me for having made that error. I am still not he.
>>>
>>>
>>>
>>> Which maybe connects to the last point; if you read my work, you would
>>> see thirty years of arguments *for* neural networks, just not in the
>>> way that you want them to exist. I have ALWAYS argued that there is a role
>>> for them;  characterizing me as a person “strongly opposed to neural
>>> networks” misses the whole point of my 2001 book, which was subtitled
>>> “Integrating Connectionism and Cognitive Science.”
>>>
>>>
>>>
>>> In the last two decades or so you have insisted (for reasons you have
>>> never fully clarified, so far as I know) on abandoning symbol-manipulation,
>>> but the reverse is not the case: I have *never* called for dismissal of
>>> neural networks, but rather for some hybrid between the two (as you
>>> yourself contemplated in 1991); the point of the 2001 book was to
>>> characterize exactly where multilayer perceptrons succeeded and broke down,
>>> and where symbols could complement them. It’s a rhetorical trick (which is
>>> what the previous thread was about) to pretend otherwise.
>>>
>>>
>>>
>>> Gary
>>>
>>>
>>>
>>>
>>>
>>> On Feb 2, 2022, at 11:22, Geoffrey Hinton <geoffrey.hinton at gmail.com>
>>> wrote:
>>>
>>> 
>>>
>>> Embeddings are just vectors of soft feature detectors and they are very
>>> good for NLP.  The quote on my webpage from Gary's 2015 chapter implies the
>>> opposite.
>>>
>>>
>>>
>>> A few decades ago, everyone I knew then would have agreed that the
>>> ability to translate a sentence into many different languages was strong
>>> evidence that you understood it.
>>>
>>>
>>>
>>> But once neural networks could do that, their critics moved the
>>> goalposts. An exception is Hector Levesque who defined the goalposts more
>>> sharply by saying that the ability to get pronoun references correct in
>>> Winograd sentences is a crucial test. Neural nets are improving at that but
>>> still have some way to go. Will Gary agree that when they can get pronoun
>>> references correct in Winograd sentences they really do understand? Or does
>>> he want to reserve the right to weasel out of that too?
>>>
>>>
>>>
>>> Some people, like Gary, appear to be strongly opposed to neural networks
>>> because they do not fit their preconceived notions of how the mind should
>>> work.
>>>
>>> I believe that any reasonable person would admit that if you ask a
>>> neural net to draw a picture of a hamster wearing a red hat and it draws
>>> such a picture, it understood the request.
>>>
>>>
>>>
>>> Geoff
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>> On Wed, Feb 2, 2022 at 1:38 PM Gary Marcus <gary.marcus at nyu.edu> wrote:
>>>
>>> Dear AI Hub, cc: Steven Hanson and Geoffrey Hinton, and the larger
>>> neural network community,
>>>
>>>
>>>
>>> There has been a lot of recent discussion on this list about framing and
>>> scientific integrity. Often the first step in restructuring narratives is
>>> to bully and dehumanize critics. The second is to misrepresent their
>>> position. People in positions of power are sometimes tempted to do this.
>>>
>>>
>>>
>>> The Hinton-Hanson interview that you just published is a real-time
>>> example of just that. It opens with a needless and largely content-free
>>> personal attack on a single scholar (me), with the explicit intention of
>>> discrediting that person. Worse, the only substantive thing it says is
>>> false.
>>>
>>>
>>>
>>> Hinton says “In 2015 he [Marcus] made a prediction that computers
>>> wouldn’t be able to do machine translation.”
>>>
>>>
>>>
>>> I never said any such thing.
>>>
>>>
>>>
>>> What I predicted, rather, was that multilayer perceptrons, as they
>>> existed then, would not (on their own, absent other mechanisms)
>>> *understand* language. Seven years later, they still haven’t, except in
>>> the most superficial way.
>>>
>>>
>>>
>>> I made no comment whatsoever about machine translation, which I view as
>>> a separate problem, solvable to a certain degree by correspondance without
>>> semantics.
>>>
>>>
>>>
>>> I specifically tried to clarify Hinton’s confusion in 2019, but,
>>> disappointingly, he has continued to purvey misinformation despite that
>>> clarification. Here is what I wrote privately to him then, which should
>>> have put the matter to rest:
>>>
>>>
>>>
>>> You have taken a single out of context quote [from 2015] and
>>> misrepresented it. The quote, which you have prominently displayed at the
>>> bottom on your own web page, says:
>>>
>>>
>>>
>>> Hierarchies of features are less suited to challenges such as language,
>>> inference, and high-level planning. For example, as Noam Chomsky famously
>>> pointed out, language is filled with sentences you haven't seen
>>> before. Pure classifier systems don't know what to do with such sentences.
>>> The talent of feature detectors -- in  identifying which member of some
>>> category something belongs to -- doesn't translate into understanding
>>> novel  sentences, in which each sentence has its own unique meaning.
>>>
>>>
>>>
>>> It does *not* say "neural nets would not be able to deal with novel
>>> sentences"; it says that hierachies of features detectors (on their own, if
>>> you read the context of the essay) would have trouble *understanding *novel sentences.
>>>
>>>
>>>
>>>
>>> Google Translate does yet not *understand* the content of the sentences
>>> is translates. It cannot reliably answer questions about who did what to
>>> whom, or why, it cannot infer the order of the events in paragraphs, it
>>> can't determine the internal consistency of those events, and so forth.
>>>
>>>
>>>
>>> Since then, a number of scholars, such as the the computational linguist
>>> Emily Bender, have made similar points, and indeed current LLM difficulties
>>> with misinformation, incoherence and fabrication all follow from these
>>> concerns. Quoting from Bender’s prizewinning 2020 ACL article on the matter
>>> with Alexander Koller, https://aclanthology.org/2020.acl-main.463.pdf
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__aclanthology.org_2020.acl-2Dmain.463.pdf%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3DxnFSVUARkfmiXtiTP_uXfFKv4uNEGgEeTluRFR7dnUpay2BM5EiLz-XYCkBNJLlL%26s%3DK-Vl6vSvzuYtRMi-s4j7mzPkNRTb-I6Zmf7rbuKEBpk%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009817691%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=q%2BDBLATHPeXbKLPG6SJGBsC7%2BWon7d%2B%2Fp8YONcozReU%3D&reserved=0>,
>>> also emphasizing issues of understanding and meaning:
>>>
>>>
>>>
>>> *The success of the large neural language models on many NLP tasks is
>>> exciting. However, we find that these successes sometimes lead to hype in
>>> which these models are being described as “understanding” language or
>>> capturing “meaning”. In this position paper, we argue that a system trained
>>> only on form has a priori no way to learn meaning. .. a clear understanding
>>> of the distinction between form and meaning will help guide the field
>>> towards better science around natural language understanding. *
>>>
>>>
>>>
>>> Her later article with Gebru on language models “stochastic parrots” is
>>> in some ways an extension of this point; machine translation requires
>>> mimicry, true understanding (which is what I was discussing in 2015)
>>> requires something deeper than that.
>>>
>>>
>>>
>>> Hinton’s intellectual error here is in equating machine translation with
>>> the deeper comprehension that robust natural language understanding will
>>> require; as Bender and Koller observed, the two appear not to be the same.
>>> (There is a longer discussion of the relation between language
>>> understanding and machine translation, and why the latter has turned out to
>>> be more approachable than the former, in my 2019 book with Ernest Davis).
>>>
>>>
>>>
>>> More broadly, Hinton’s ongoing dismissiveness of research from
>>> perspectives other than his own (e.g. linguistics) have done the field a
>>> disservice.
>>>
>>>
>>>
>>> As Herb Simon once observed, science does not have to be zero-sum.
>>>
>>>
>>>
>>> Sincerely,
>>>
>>> Gary Marcus
>>>
>>> Professor Emeritus
>>>
>>> New York University
>>>
>>>
>>>
>>> On Feb 2, 2022, at 06:12, AIhub <aihuborg at gmail.com> wrote:
>>>
>>> 
>>>
>>> Stephen Hanson in conversation with Geoff Hinton
>>>
>>>
>>>
>>> In the latest episode of this video series for AIhub.org
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttp-3A__AIhub.org%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3DxnFSVUARkfmiXtiTP_uXfFKv4uNEGgEeTluRFR7dnUpay2BM5EiLz-XYCkBNJLlL%26s%3DeOtzMh8ILIH5EF7K20Ks4Fr27XfNV_F24bkj-SPk-2A%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009973905%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=P3WO36jn%2B4E5%2Bt%2BqdBibO2kXwKYUEUj9jDWQly677zU%3D&reserved=0>,
>>> Stephen Hanson talks to  Geoff Hinton about neural networks,
>>> backpropagation, overparameterization, digit recognition, voxel cells,
>>> syntax and semantics, Winograd sentences, and more.
>>>
>>>
>>>
>>> You can watch the discussion, and read the transcript, here:
>>>
>>>
>>> https://aihub.org/2022/02/02/what-is-ai-stephen-hanson-in-conversation-with-geoff-hinton/
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__aihub.org_2022_02_02_what-2Dis-2Dai-2Dstephen-2Dhanson-2Din-2Dconversation-2Dwith-2Dgeoff-2Dhinton_%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3Dyl7-VPSvMrHWYKZFtKdFpThQ9UTb2jW14grhVOlAwV21R4FwPri0ROJ-uFdMqHy1%26s%3DOY_RYGrfxOqV7XeNJDHuzE--aEtmNRaEyQ0VJkqFCWw%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009973905%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=B7CedNdKS2LOcYFRVGlIC%2BtO32o0MLbq4YgWOus8rBE%3D&reserved=0>
>>>
>>>
>>>
>>> About AIhub:
>>>
>>> AIhub is a non-profit dedicated to connecting the AI community to the
>>> public by providing free, high-quality information through AIhub.org
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttp-3A__AIhub.org%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3DxnFSVUARkfmiXtiTP_uXfFKv4uNEGgEeTluRFR7dnUpay2BM5EiLz-XYCkBNJLlL%26s%3DeOtzMh8ILIH5EF7K20Ks4Fr27XfNV_F24bkj-SPk-2A%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009973905%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=P3WO36jn%2B4E5%2Bt%2BqdBibO2kXwKYUEUj9jDWQly677zU%3D&reserved=0>
>>> (https://aihub.org/
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__aihub.org_%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3Dyl7-VPSvMrHWYKZFtKdFpThQ9UTb2jW14grhVOlAwV21R4FwPri0ROJ-uFdMqHy1%26s%3DIKFanqeMi73gOiS7yD-X_vRx_OqDAwv1Il5psrxnhIA%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009973905%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=vEcVelgUzYKss53xDMh7g%2BPWfsrf%2BydW2SBma3oTkew%3D&reserved=0>).
>>> We help researchers publish the latest AI news, summaries of their work,
>>> opinion pieces, tutorials and more.  We are supported by many leading
>>> scientific organizations in AI, namely AAAI
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__aaai.org_%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3Dyl7-VPSvMrHWYKZFtKdFpThQ9UTb2jW14grhVOlAwV21R4FwPri0ROJ-uFdMqHy1%26s%3DwBvjOWTzEkbfFAGNj9wOaiJlXMODmHNcoWO5JYHugS0%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009973905%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=mooy8W%2Bdbj1cfA4y7ds7AKTpvSjG6j8LaCc9nORQfhg%3D&reserved=0>,
>>> NeurIPS
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__neurips.cc_%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3Dyl7-VPSvMrHWYKZFtKdFpThQ9UTb2jW14grhVOlAwV21R4FwPri0ROJ-uFdMqHy1%26s%3D3-lOHXyu8171pT_UE9hYWwK6ft4I-cvYkuX7shC00w0%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009973905%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=TBajU%2B1cgSkp%2Fx0e2p%2FEtQaCz%2F3hCRaZuSp2ZfffXHE%3D&reserved=0>,
>>> ICML
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__icml.cc_imls_%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3Dyl7-VPSvMrHWYKZFtKdFpThQ9UTb2jW14grhVOlAwV21R4FwPri0ROJ-uFdMqHy1%26s%3DJJyjwIpPy9gtKrZzBMbW3sRMh3P3Kcw-SvtxG35EiP0%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009973905%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=ruboOy7nl6zzRMEqrrSXDHEpyJPLVobkJhg0NJXF8kQ%3D&reserved=0>,
>>> AIJ
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__www.journals.elsevier.com_artificial-2Dintelligence%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3Dyl7-VPSvMrHWYKZFtKdFpThQ9UTb2jW14grhVOlAwV21R4FwPri0ROJ-uFdMqHy1%26s%3DeWrRCVWlcbySaH3XgacPpi0iR0-NDQYCLJ1x5yyMr8U%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009973905%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=dbQN2Cmfmx8sfEPsPqbzs%2BY08elmLXaX7ycliUnnSb4%3D&reserved=0>
>>> /IJCAI
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__www.journals.elsevier.com_artificial-2Dintelligence%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3Dyl7-VPSvMrHWYKZFtKdFpThQ9UTb2jW14grhVOlAwV21R4FwPri0ROJ-uFdMqHy1%26s%3DeWrRCVWlcbySaH3XgacPpi0iR0-NDQYCLJ1x5yyMr8U%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009973905%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=dbQN2Cmfmx8sfEPsPqbzs%2BY08elmLXaX7ycliUnnSb4%3D&reserved=0>,
>>> ACM SIGAI
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttp-3A__sigai.acm.org_%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3Dyl7-VPSvMrHWYKZFtKdFpThQ9UTb2jW14grhVOlAwV21R4FwPri0ROJ-uFdMqHy1%26s%3D7rC6MJFaMqOms10EYDQwfnmX-zuVNhu9fz8cwUwiLGQ%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009973905%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=0bf4tH%2Bq%2B4vpME%2FvfX00b7GopTiSIW1%2BcL7u2Q9fxNg%3D&reserved=0>,
>>> EurAI/AICOMM, CLAIRE
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__claire-2Dai.org_%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3Dyl7-VPSvMrHWYKZFtKdFpThQ9UTb2jW14grhVOlAwV21R4FwPri0ROJ-uFdMqHy1%26s%3D66ZofDIhuDba6Fb0LhlMGD3XbBhU7ez7dc3HD5-pXec%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009973905%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=CxrUEzAjP93Gd0Gac5bXT0StPrT3yThC%2F4h7rOnPzRo%3D&reserved=0>
>>> and RoboCup
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__www.robocup.org__%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3Dyl7-VPSvMrHWYKZFtKdFpThQ9UTb2jW14grhVOlAwV21R4FwPri0ROJ-uFdMqHy1%26s%3DbBI6GRq--MHLpIIahwoVN8iyXXc7JAeH3kegNKcFJc0%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009973905%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=T9u4XHGbeeqoC5%2B069VueFyIWmY3X1kWyl0rFWxd8yQ%3D&reserved=0>
>>> .
>>>
>>> Twitter: @aihuborg
>>>
>>>
>>>
>>>
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__www.avast.com_sig-2Demail-3Futm-5Fmedium-3Demail-26utm-5Fsource-3Dlink-26utm-5Fcampaign-3Dsig-2Demail-26utm-5Fcontent-3Dwebmail%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3DwaSKY67JF57IZXg30ysFB_R7OG9zoQwFwxyps6FbTa1Zh5mttxRot_t4N7mn68Pj%26s%3DAo9QQWtO62go0hx1tb3NU6xw2FNBadjj8q64-hl5Sx4%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009973905%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=z0HZYsbEu%2BZCfzxRnZetHEm15zN4jnc9%2BlUdHQ1zstc%3D&reserved=0>
>>>
>>> Virus-free. www.avast.com
>>> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.proofpoint.com%2Fv2%2Furl%3Fu%3Dhttps-3A__www.avast.com_sig-2Demail-3Futm-5Fmedium-3Demail-26utm-5Fsource-3Dlink-26utm-5Fcampaign-3Dsig-2Demail-26utm-5Fcontent-3Dwebmail%26d%3DDwMFaQ%26c%3DslrrB7dE8n7gBJbeO0g-IQ%26r%3DwQR1NePCSj6dOGDD0r6B5Kn1fcNaTMg7tARe7TdEDqQ%26m%3DwaSKY67JF57IZXg30ysFB_R7OG9zoQwFwxyps6FbTa1Zh5mttxRot_t4N7mn68Pj%26s%3DAo9QQWtO62go0hx1tb3NU6xw2FNBadjj8q64-hl5Sx4%26e%3D&data=05%7C01%7Ctgd%40oregonstate.edu%7C6c8cc9dafd744c179d1408da65d58603%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C637934265009973905%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=z0HZYsbEu%2BZCfzxRnZetHEm15zN4jnc9%2BlUdHQ1zstc%3D&reserved=0>
>>>
>>>
>>>
>>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20220718/218e4c70/attachment-0001.html>