Loligo Blog - Neural Networks

Language and Schizophrenia Lecture -- Robert Sapolsky, Stanford

nospam@example.com (John R) — Fri, 12 Apr 2013 00:08:00 -0700

This is a May 2010 lecture given by Professor Robert Sapolsky at Stanford University. The lecture is on schizophrenia, but starts with a very informative lecture on language. Specifically, it's about what is shaping up to be the genetic, bio-molecular correlates of grammar and language.

Warning: For most lecturers you can kind-of do little fast-forward jumps during the video, resynchronizing your cognitive-following groove after each jump. This can shave some time off the lecture.

With this guy, that's not so easy. He really loads you up with information. (I'd love to see him do a lecture on autism).

http://www.youtube.com/watch?v=nEnklxGAmak

Viewing note: This starts with a wrap-up on a previous lecture on language and linguistics. The Schizophrenia lecture begins at around 23:30.

Multitemporal Synapses and Our Perception of a Present Moment

nospam@example.com (John R) — Thu, 19 Apr 2012 20:44:00 -0700

Overview

“Certainly, one of the most relevant and obvious characteristics of a present moment is that it goes away, and that characteristic must be represented internally.”

Stated plainly[1], the principle behind multitemporal synapses is that we maintain the blunt “residue” of past lessons in long-term connections, while everything else is quickly forgotten, and learned over again, in the instant. In other words, we re-learn the detailed parts of our responses as we are confronted with each new current situation.[2]

One of the primary benefits of applying this principle, in the form of multitemporal synapses, is a neural network construct that is completely free of the usual problems associated with catastrophic forgetting. When you eliminate catastrophic forgetting from your neural network structure, the practical result is the ability to develop networks that continuously learn from their surroundings, just like their natural counterparts.

. . . . . . .
Contents

A Two Time-Span Explanation

^[top]

A Major Problem With Neural Networks

One major challenge with conventional neural network models has been in how to maintain connections that store enough intricate in-the-moment response-details to deal with any contingency that the system may encounter. Conventionally, such details would overwhelm long-term lessons stored in permanent weights. This characteristic of conventional neural network models is known as The Stability Plasticity Problem, and is the underlying cause of "catastrophic forgetting."

When an artificial neural network that has learned a training set of responses, then encounters a new response to be learned, the result is usually ‘catastrophic forgetting’ of all earlier learning. Training on the new detail alters connections that are maintained by the network in a holistic (global) fashion. Because of this, it is almost certain that such a change will radically alter the outputs that were desired for the original training set.

Continue reading "Multitemporal Synapses and Our Perception of a Present Moment"

The McGurk Effect

nospam@example.com (John R) — Mon, 19 Mar 2012 08:43:00 -0700

The McGurk effect is a perception illusion, which shows how our perception of reality can be affected by interactions between multiple senses. The presentation of the McGurk effect demonstrated in the following video also shows, convincingly, that our visual processes can completely override our auditory perceptions of speech — at least in certain circumstances.

http://www.youtube.com/watch?v=G-lN8vWm3m0

^[top]

Hearing With Our Eyes

In the above video, you will see the speaker's lips form an 'f'-sound. You will “hear” an 'f'-sound even though the actual sound being produced is a 'b'-sound (dubbed in over the video).

In this video, the 'f' perception reported by your eyes completely overrides the 'b' perception reported by your ears. Can we conclude, from this, that visual processing in the brain is given full priority over auditory processing?

That may be a bit hasty.

Continue reading "The McGurk Effect"

AI - Time for a New Name?

nospam@example.com (John R) — Thu, 05 Jan 2012 09:33:00 -0700

Linguists have recently discovered [1] that almost all words are metaphorical at their base, and some people (e.g., me) posit that they all are. Though speculative, it is at least conceivable that even the sub-language signaling in the brain, which eventually leads to language, is also metaphorical. Consider that the bell may become a metaphor for food in the mind of Pavlov's dog.

Language is also able to relate ambiguity about the concepts it conveys. The word “life,” for example, can mean life-biology, or life-consciousness. Up until now, it has been perfectly acceptable to use these two meanings interchangeably. There simply has never been an instance of consciousness that existed outside of a biological body — at least none that we could directly experience with our physical senses.

Things may be changing now. . .

Continue reading "AI - Time for a New Name?"

Learning is Adaptation is Learning - Using Batesian Mimicry As an Explanatory Device

nospam@example.com (John R) — Thu, 03 Nov 2011 13:11:00 -0700

The book on the Netlab project often returns to the notion that learning is merely a form of adaptation and that, conversely, adaptation is merely a form of long-term learning. This, in turn, all fits under the umbrella notion that memory is behavior.

The idea that learning is adaptation is learning is forwarded as a possibility, mainly as a better means of discussing the concepts. This (in my opinion) provides a clearer and more converged understanding of how memory works in biological organisms. This could be very wrong, of course, so it's important to describe it properly. That way it, and not a straw man, can be critiqued. This article represents one such attempt to properly describe it. . .

Batesian Mimicry

Batesian mimicry is when a non-noxious/non-poisonous plant or animal projects the appearance of a poisonous plant or animal, allowing it to avoid being eaten by predators.

Those predators, goes the logic, which have partaken of the poisonous organism and survived, would have become very sick, and would have learned to avoid ingesting anything that appears to be that organism in the future. This will include those organisms who are not poisonous, but merely look, or act, like the poisonous organism.

Continue reading "Learning is Adaptation is Learning - Using Batesian Mimicry As an Explanatory Device"

Neural Networks Backgrounder: Ce n'est pas une l'histoire

nospam@example.com (John R) — Mon, 03 Oct 2011 08:24:00 -0700

Overview

This article provides a layman's-level discussion of neural network technology within the framework of a sketchy historical sequence. Neural networks are described while presenting an overview of just one of the many routs taken by the field in the last half-century or so.

It is not for those interested in a full history of neural networks (i.e., connectionism). It is just a quick backgrounder, which should suffice to give readers a little bit of perspective into how we got from "there" to "here." The actual history of this field is storied, and sometimes even checkered and controversial. I highly recommend to anybody who is interested, that you get a good book or two on the subject.

This entry will also serve as a place to accumulate links to resources and information on the subject of neural networks and their history at this layman's level.

. . . . . . .
Contents

Continue reading "Neural Networks Backgrounder: Ce n'est pas une l'histoire"

UC Berkeley - Scientists use brain imaging to reveal the movies in our mind

nospam@example.com (John R) — Sat, 24 Sep 2011 12:41:21 -0700

Scientists at UC Berkeley have taken brain scans of subjects in an fMRI machine while they watched a movie clip. They then reconstructed the movie the subjects were watching using only the brain scan data, and a database of 18 million seconds of random video gleaned from the web.

First, they used fMRI imaging to measure brain activity in visual cortex as a person looked at several hours of movies. They then used those data to develop computational models that could predict the pattern of brain activity that would be elicited by any arbitrary movies (i.e., movies that were not in the initial set). Next, they used fMRI to measure brain activity elicited by a second set of movies that were also distinct from the first set. Finally, they used the computational models to process the elicited brain activity, and reconstruct the movies in the second set.

The amount of new understanding this could allow us to gather about mind-brain correlates and first person knowledge should be considerable. If this lives up to the hype, a lot of new research ideas should come out of it. Keeping fingers crossed here.

In the above clip - the movie that each subject viewed while in the fMRI is shown in the upper left position. Reconstructions for three subjects are shown in the three rows at bottom. All these reconstructions were obtained using only each subject's brain activity and a library of 18 million seconds of random YouTube video that did not include the movies used as stimuli. The reconstruction at far left is the Average High Posterior (AHP). The reconstruction in the second column is the Maximum a Posteriori (MAP). The other columns represent less likely reconstructions. The AHP is obtained by simply averaging over the 100 most likely movies in the reconstruction library. These reconstructions show that the process is very consistent, though the quality of the reconstructions does depend somewhat on the quality of brain activity data recorded from each subject. [source: Gallant Lab (see resources below)]

Continue reading "UC Berkeley - Scientists use brain imaging to reveal the movies in our mind"

Multitemporal Synapses Awarded a Patent

nospam@example.com (John R) — Thu, 10 Mar 2011 11:15:28 -0700

YEAH baby!

A neural network innovation described in the book: Netlab Loligo has been awarded a patent (#7,904,398). — Of the innovations described in the book, it is the second to receive letters patent (so far ). The patent is titled:

“Artificial Synapse Component Using Multiple Distinct Learning Means With Distinct Predetermined Learning Acquisition Times”
Patent titles serve mainly as an aid for future patent searchers. The patented innovation, along with the underlying concepts and principles that led to it are described and discussed in the book, where they are simply referred to as “Multitemporal Synapses.”

The primary advantage imparted by the innovation is that it gives adaptive systems a present moment in time. This allows them to quickly and intricately adapt to the detailed response needs of their present situation, without cluttering up long term memories with the minute details of those responses.

Sources & Resources

Multitemporal Synapses and Our Perception of a Present Moment
Stated simply, the theory behind multitemporal synapses is that we maintain the blunt essence of past lessons in long-term connections. Everything else is RE-learned in the moment.

Multitemporal Synapses
This is a blog entry here that tries to describe Multitemporal Synapses. When time permits, I will try to provide a new blog entry with a clearer explanation using book excerpts (P.S. see above entry). It will be specifically geared to laymen. If you are interested, please subscribe to the feed.

Influence Learning Gets A Patent
Influence Based Learning was the first of Netlab's innovations to be granted a patent. This latest patent makes two (and counting, stay tuned).

[pdf] Patent Title Page

Official Gazette Entry at the Patent Office [TEMPORARY LINK]

Biological Underpinnings of Influence Learning

nospam@example.com (John R) — Thu, 03 Mar 2011 17:28:00 -0700

The Netlab development effort has led to a new method and device that produces learning factors for pre-synaptic neurons. The need to provide learning factors for pre-synaptic neurons was first addressed by backpropagation (Werbos, 1974). The new method differs from backpropagation in that its use is not restricted to feed-forward only networks. This new learning algorithm and method, called Influence Learning, is described here and in other entries in this blog (see Resources section below) .

Influence Learning is based on a simple conjecture. It assumes that those forward neurons that are exercising the most influence over responses to the immediate situation will be more attractive to pre-synaptic neurons. That is, for the purpose of forming or strengthening connections, active pre-synaptic neurons will be most attracted to forward neurons that are exercising the most influence.

Perhaps the most relevant thing to understand about this process is that these determinations are based entirely on activities taking place while signals (stimuli) are propagating through the network. Unlike backpropagation, there is no need for an externally generated error signal to be pushed through the network, in backwards order, and in ever diminishing magnitudes.

Support In Biological Observations

While influence learning in artificial neural network simulations is new, it is based on biological observations and underpinnings from discoveries made over twenty years ago. One of the biological observations that led to the above speculation about attraction to the exercise of influence was discussed briefly in the book The Neuron: Cell and Molecular Biology.

An experiment described in that book shows what happens when you cut (or pharmacologically block) the axon of a target neuron. In that experiment the pre-synaptic connections to the target neuron began to retract after its axon was cut. That is, the axons making presynaptic connections to the modified neuron went away when it no longer made synaptic connections to its own post-synaptic neurons.

The book also described how, when the target neuron’s axon was unblocked (or grew back), the axons from presynaptic neurons immediately began to reform and re-establish connections with the target. Based on these observations, the following possibility was asserted.

"...Maintenance of presynaptic inputs may depend on a post-synaptic factor that is transported from the terminal back toward the soma."

The following diagram depicts these observations schematically.

Continue reading "Biological Underpinnings of Influence Learning"

Introducing: Multitemporal Synapses

nospam@example.com (John R) — Tue, 25 Jan 2011 20:21:00 -0700

A set of constructs and methods introduced and described in the book: Netlab Loligo will improve the ability of systems constructed with them to adapt to current short-term situations, and learn from those short-term experiences over the long term.

A New Learning Theory That Predicts A “Present Moment”

How do we, as biological organisms, manage to keep so much finely detailed information in our brains about how to respond to any given situation? That is, how do we manage to keep countless tiny intricacies stored away in our “subconscious” ready to be called upon at just the right time, right when we need them in the present moment?

According to this theory of learning, the answer to that question is: We don't.

Instead, our long term connections—those that immediately drive our responses at all times—are only concerned with getting us started in any given “present.” Responses stored in long-term connections start us along a trajectory that makes it easier for us to learn whatever short-term, detailed responses are needed for any given detailed situation.

Connections that drive short-term responses, on the other hand, form spontaneously in-the-moment, and quickly adapt to whatever present situation we currently find ourselves in. Just as significantly, connections driving short-term responses tend to dissipate as quickly as they form. This theory essentially says that each connection in the brain that drives responses (physical or internal) includes multiple distinct connection strengths, which each increase and decrease at different rates of speed.

How It's Done

Multi-temporality is achieved in Netlab's simulation environment by providing multiple weights per a connection point (i.e., synapse), which are referred to as Multitemporal^{[Note 1]} synapses. Multitemporal synapses employ multiple weights. Each of the multiple weights associated with a given synapse represents a connection strength, and can be set to acquire and retain its strength at a different rate from the others. The methods also specify Weight-To-Weight Learning, which is a means of teaching a given weight in the set of multiple weights, using the value of other weights from the same connection. Together these constructs provide all the functionality required to model the theory of learning discussed above.

Following is a graphic excerpted from the book: Netlab Loligo, which shows a neuron containing three different weights for each connection point. Each weight is given its own learning algorithms, with its own learning-rate, and forget-rate.

Continue reading "Introducing: Multitemporal Synapses"

See Every Synapse and Its Type - Stanford's New Imaging Technique

nospam@example.com (John R) — Wed, 17 Nov 2010 16:10:00 -0700

3D + Context

Stanford University School of Medicine has developed a relatively simple new imaging technique that provides a very exact way to capture the synapses of a connectome with pinpoint 3D positional accuracy, and considerable contextual resolution.

Stanford has performed a study (see below), which was admittedly done primarily just to showcase the new technique. That said, the study managed to produce a very impressive new find.

“ In the course of the study, whose primary purpose was to showcase the new technique’s application to neuroscience, Smith and his colleagues discovered some novel, fine distinctions within a class of synapses previously assumed to be identical. ”

Continue reading "See Every Synapse and Its Type - Stanford's New Imaging Technique"

Influence Learning Gets A Patent

nospam@example.com (John R) — Sun, 17 Oct 2010 09:31:00 -0700

Woo HOOO!

Influence Based Learning, one of two new learning methods described in the book Netlab Loligo, has just been awarded a United States Patent. The official title of the patent is:

“Feedback-Tolerant Method And Device Producing Weight-Adjustment Factors For Pre-Synaptic Neurons In Artificial Neural Networks”
The title is a mouthful, primarily designed to help future patent searchers determine if their great idea has already been discovered and patented. It is fully described and discussed in the book, where it is simply referred to as Influence Learning.

As the patent-title expresses, one of the benefits it imparts over existing learning algorithms, is that it is feedback-tolerant. It will work fine with the current-day feed-forward networks configured as "slabs", but it also allows connecting neurons to pre-synaptic neurons as well. That is, it allows feedback, which means you don't have to configure your network with "hidden layers" anymore if you don't want to. You are free to use any connectome you'd like.

[pdf] Patent Title Page
Neural Networks Backgrounder: Ce n'est pas une l'histoire
A quick backgrounder on neural networks presented in a sketchy semi-historical format.

Introducing: Influence Learning

nospam@example.com (John R) — Tue, 07 Sep 2010 12:14:00 -0700

Influence learning is one of two new learning algorithms that have emerged (so far) from the Netlab development effort. This blog entry contains a brief overview describing how it works, and some of the advantages it brings to the task of neural network weight-adjustment.

How It Works

This learning method is based on the notion that—like their collective counterparts—neurons may be attracted to, and occasionally repulsed by, the exercise of influence by others. In the case of neurons, the "others" would be other neurons. As simple as that notion sounds, it produces a learning method with a number of interesting benefits and advantages over the current crop of learning algorithms.

A neuron using influence learning is not nosy, and does not concern itself with how its post-synaptic (forward) neurons are learning. It simply trusts that their job is to learn, and that they are doing their job. In other words, a given neuron fully expects, and assumes that other neurons within the system are learning. Each one treats post-synaptic neurons that are exercising the most influence as role models for adjusting connection-strengths. The norm is for neurons to see influential forward neurons as positive role models, but neurons may also see influential forward neurons as negative role models.

It Is Simple

As you might guess, the first benefit is simplicity. The method does not try to hide a lack of new ideas behind a wall of new computational complexity. It is a simple, new, method based on a simple, almost axiomatic, observation, and it can be implemented with relatively little computational power.

It Imposes No Restrictions On Feedback

Influence Learning is completely free of feedback restrictions. That is, network connection-structures may be designed with any type, or amount of feedback looping. The learning mechanism will continue to be able to properly adapt connection-strengths regardless of how complex the feedback scheme is. The types of feedback designers are free to employ include servo feedback, which places the outside world (or some network structure that is closer to the outside world) directly in the signaling feedback path.

This type of "servo-feedback" is shown graphically in figure 6-5 of the book, which has been re-produced here.

Continue reading "Introducing: Influence Learning"

Evidence for Myosin II Mediation of Short- to Long-Term Memory Formation

nospam@example.com (John R) — Tue, 31 Aug 2010 12:28:00 -0700

One of Netlab's synapse mechanisms and structures is based loosely on a silent-synapse hypothesis of long- vs short-term memory, in which short and long both occur at the same connection-point (synapse). Netlab includes a learning method based on this as well, called weight-to-weight learning. The silent synapse phenomenon has been observed for quite some time in biological studies, and there has been very good evidence to explain some of the underlying mechanisms responsible for the observation. Still there have been many missing pieces to the puzzle.

An Interesting Study

Recently there has been a development that seems to give evidence and details to a related theory/hypothesis of how synapse strength may be mediated through a molecular motor called Myosin II on the post-synaptic side. So suggests one study out of The Scripps Research Institute.

It has been thought for some time now (see background information below) that molecular motors resembling those used to produce movement in muscle tissue, may be a major player in the processes mediating the transfer of memory-connections from short-, to long-term on the post-synaptic side. We now seem to be getting to more detailed understanding of the mechanisms underlying these phenomena. Like so many brain constructs, there does seem be a great deal of variety.

The vernacular that seems to be emerging is that these mechanisms "stabilize" the connection strengths. This might still be jumping the gun on the conclusions, but it is not a bad way to think about it for now.

Sources & Resources

Scripps Research Scientists Uncover New Mechanism of Memory Formation.
This is a news story about the study.

Abstract and link to article (full=$)
This gets you to the article from the journal Neuron (full text is behind a pay wall)
Gavin Rumbaugh
Are you ready to Rumbaugh? i'm sure he's never heard that joke before

Related/Background:

[pdf] Remodeling the Plasticity Debate: The Presynaptic Locus Revisited
A really interesting paper from 2006 published at the journal Physiology. From its description: "The cellular mechanisms contributing to long-term potentiation and activity-induced formation of glutamatergic synapses have been intensely debated. Recent studies have sparked renewed interest in the role of presynaptic components in these processes. Based on the present evidence, it appears likely that long-term plasticity utilizes both pre- and postsynaptic expression mechanisms."

Silent Synapses in Neural Plasticity: Current Evidence
Great article from 1999 gets you a nice sense of the time-line to that point.

CSHL show in unprecedented detail how cortical nerve cells form synapses with neighbors
Related.

Actuators (scroll to bottom)
A blog-post here about actuators. Mostly robotics, but a section at the bottom has a couple of nice videos describing the function and structure of animal muscles.

The Neuron: Cell and Molecular Biology (Amazon.com)
A primary reference work, which is listed as the primary reference in Netlab. You will find information on the silent synapse hypothesis here.

Memory's Master Switch: Molecular Power Behind Memory Discovered
Related/Background

[pdf] Scientists discover major clue in long-term memory making
Related/Background

Diffuse-to-Focal vs Local-to-Distributed: Not an Either-Or Choice

nospam@example.com (John R) — Mon, 23 Aug 2010 11:51:00 -0700

As a programmer I find it very satisfying when a phony false choice is taken down. Chris Chatham, who maintains Developing Intelligence blog looks like he's hot on the trail of one.

In his post titled: Neural Mechanisms Giving Rise to Diffuse-to-Focal and Local-to-Distributed Developmental Shifts he has provided a run-down of some of the best observational support showing evidence for the diffuse to focal shift. He then explores and teaches some evidence for the local-to-distributed shift, which, it turns out, is just as convincing.

Here's a cool visualization from the article used to clarify the local-to-distributed data:**

He provides a very good explanation for the apparent disagreement in the experimental data. His conclusion? The two aren't mutually exclusive. (thank you Mr. Chatham)

So, how does this work? Is the brain just big enough to accommodate two different mechanisms? Possibly, but Chatham also explores a distinct possibility that the same underlying mechanisms may be responsible for both types of development. It turns out there is a bit of good reason to think it is the latter.

= = = = = = = = = = =
Notes:

** Okay, I don't know how much clarity it brings, but it is a slick visualization, therefor, it makes it into the post.