Connectionists: Transient subnetwork selection: a new paradigm to replace connectionism?

[Rothganger, Fredrick]

It's great to see papers which discuss neuroscience mechanisms and form theories about how they implement the mind. We should think of the many diverse mechanisms of neural processing in a holistic way. What do they accomplish while all working together? The spike-based movement of signals is doubtless an important part of a complete theory of neural processing. Likewise, mechanisms that regulate how neurons respond, and how they make structural changes over longer time scales are also important. New discoveries in neuroscience come out every year. It is no exaggeration to say that there are hundreds of mechanisms waiting to be incorporated into a working theory of brain function.


________________________________
From: Connectionists <connectionists-bounces at mailman.srv.cs.cmu.edu> on behalf of Danko Nikolic <danko.nikolic at gmail.com>
Sent: Tuesday, January 31, 2023 10:43 AM
To: Post Connectionists <connectionists at mailman.srv.cs.cmu.edu>
Subject: [EXTERNAL] Connectionists: Transient subnetwork selection: a new paradigm to replace connectionism?

Dear all,

I am happy to announce that my paper, the draft of which has been discussed on this list, has yesterday finally been published after a peer review.

This is probably the most important paper I have done in my career so far.

To remind you, the paper proposes a new paradigm as an alternative to connectionism. To understand the mind, synapses are not so important any more. Instead, critical are some other types of proteins on the neural membrane. These proteins have the capability to transiently select subnetworks that will be functional in the next few seconds or minutes. The paradigm proposes that cognition emerges from those transient subnetwork selections (and not from network computations of the classical, the so-called connectionist paradigm). The proteins in question are metabotropic receptors and G protein-gated ion channels. Simply put, we think with those proteins. A result of a thought is a new state of network pathways, not the activity of neurons.

I would like to thank the list for many of the comments that I received and that helped me improve the manuscript. For example, very useful was the information on the learning algorithms able to learn the n-bit parity problem (aka, generalized XOR), which I used to illustrate the scaling problems of deep learning. This made my supplementary materials much better.

The paper can be downloaded without a paywall for 50 days, here:
https://authors.elsevier.com/a/1gVvg5Fq7aXeir<https://gcc02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fauthors.elsevier.com%2Fa%2F1gVvg5Fq7aXeir&data=05%7C01%7Cfrothga%40sandia.gov%7C0b3d655d48ac455f84c208db042a1b9c%7C7ccb5a20a303498cb0c129007381b574%7C1%7C0%7C638108351143972771%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=1vQl5kuAMaewYRx%2FbrIvEuuf1s6XFR%2BP7NRHZeDVRFY%3D&reserved=0>

The new version of the paper is much better than the original draft. It has more information, clearer explanations and improved structure.

I hope the paper inspires people to investigate possibilities beyond connectionism both for understanding the brain and for building AI.

For myself, I would love to build an AI based on these principles.

Thanks a lot.

Danko


Dr. Danko Nikolić
www.danko-nikolic.com<https://gcc02.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.danko-nikolic.com%2F&data=05%7C01%7Cfrothga%40sandia.gov%7C0b3d655d48ac455f84c208db042a1b9c%7C7ccb5a20a303498cb0c129007381b574%7C1%7C0%7C638108351143972771%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=lBI382%2FXMUq3VjpQZ%2BPRmrLKtiOmHdEAta4MjEv6CQA%3D&reserved=0>
https://www.linkedin.com/in/danko-nikolic/<https://gcc02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.linkedin.com%2Fin%2Fdanko-nikolic%2F&data=05%7C01%7Cfrothga%40sandia.gov%7C0b3d655d48ac455f84c208db042a1b9c%7C7ccb5a20a303498cb0c129007381b574%7C1%7C0%7C638108351143972771%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=RYQ7%2FrcSLolW%2BmvzxaAIk7y%2ByKKV9rRxzmNvPVAK%2F5E%3D&reserved=0>
-- I wonder, how is the brain able to generate insight? --

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20230201/c01a08bd/attachment.html>