Loligo Blog - Science & Tech

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"

Goodbye, World - Dennis Ritchie Creator of C Has Died

nospam@example.com (John R) — Wed, 12 Oct 2011 17:43:00 -0700

Dennis Ritchie, the creator of the C programming language, died on Saturday after battling a long illness. The C programming language, arguably, changed the world. It can be found at the heart of most modern computer applications, operating systems, and successor programming languages.

   Dennis Ritchie
   Creator of the C programming language

   9 September 1941 — 8 October 2011



There's an obituary, and a very well researched history, at the Guardian

From his book, "The C Programming Language"

main()
{
        printf("hello, world\n");
}

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"

True Random Number Generator Using Only Logic Gates?

nospam@example.com (John R) — Wed, 07 Sep 2011 15:42:00 -0700

In the book, Netlab Loligo, repeated calls are made for true random number generators (TRNGs) to be included in all CPUs, or at least in those that are intended for use in neural network applications. Naturally, I was very excited to see a headline about Intel having developed one with general purpose use in mind.

Intel's Low-Power “True” Random Number Generator

IEEE has an article about a new “true” random number generator from Intel that has been 10 years in development. Its primary advantage is that, while it is a true RNG, it operates entirely in digital mode using digital devices to obtain randomness from hardware. The slow, energy hogging, analog technology normally needed to glean randomness from Quantum phenomena has been eliminated. It has a few quirks, such as the need to force the outputs of its two mutex inverters high, and the seemingly unavoidable need to compensate using averaging techniques. I expand just a little on these quirks below.

In the spirit of not critiquing something without also offering, at least, a sincere attempt at a solution, I've forwarded a quick (if dirty) attempt at an “all logic gates” DTRNG (Digital True Random Number Generator) below. Only the equations were scratched out at the IEEE blog, I've since produced a circuit diagram graphic, which is included here as well.

Continue reading "True Random Number Generator Using Only Logic Gates?"

Robot Arm Inventor Dies

nospam@example.com (John R) — Thu, 11 Aug 2011 09:59:00 -0700

George Charles Devol
Inventor of Robot Arm

20 February 1912 — 11 August 2011

The self taught inventor of the robotic arm, which has become an icon of factory automation from Detroit to Asia, has died.

Story: Pioneer of the long arm of factory floor technology

Four New Species of Zombifying Ant Fungus Found

nospam@example.com (John R) — Tue, 17 May 2011 19:43:52 -0700

From the press release: “Once infected by spores, the worker ants ... leave the nest, find a small shrub and start climbing. The fungi directs all ants to the same kind of leaf: about 25 centimeters [(9.8 inches)] above the ground and at a precise angle to the sun (though the favored angle varies between fungi). How the fungi do this is a mystery.”

[. . .article]

The paper:

Hidden Diversity Behind the Zombie-Ant Fungus Ophiocordyceps unilateralis: Four New Species Described from Carpenter Ants in Minas Gerais, Brazil

Background & Further Reading.

A few interesting links to related stuff. Includes some strange and interesting background about ants.

Youtube short video about Cordyceps fungi
Ant Colony Optimization Site - Behavior of real ants
AntWeb
AntBase (database of ants)
Ant Genera Distribution Maps
Bug Guide
Honey Ants
Ant Death Spiral
- Ant Spiral Video

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"

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"

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.

Experimenter: Bring Your Own Razor - (book excerpt)

nospam@example.com (John R) — Tue, 17 Aug 2010 14:58:00 -0700

The following excerpts from Chapter 4 of the book ("Our Metaphysical Tool Shed") may help to clarify the point of this post.

Anti-Razor¹

It would probably be sufficient to simply express the weighted result as a ratio, but for now that's just one option. As our understanding grows, we may find that our maintaining two separate sums and many of the other values, is the metaphorical equivalent of gluing feathers to the wings of a flying machine. . .

. . .

1. This sub-heading is a reference to Ockham's razor, which is almost always mis-characterized in common usage. William of Ockham's original advice is based on sound, logical, reasoning, while the common mis-characterization is essentially a fashion statement. Here, however, I argue that programmers must give experimenters the ability to define their own (real) razors, and so should not mandate them in the modeling tools we provide. That is, we should give experimenters more, and let them decide for themselves how to divide and conquer those “more” into “fewer”.

Many of the ANN modeling tools available today are merely paint-by-number kits, which allow experimenters to try out solutions that other people have worked out and documented in formulaic recipes. Netlab is decidedly NOT among these offerings.

The known neural network formulas, for example, each represent somebody else's abstraction, and reduction of the observation data. The function produced is essentially a workable, defined, recipe for creating an effect that is similar to observed behaviors. In short, the person who came up with the formula in the first place was the one who did all the heavy lifting.

Experimenters should be given tools that let them find and test their own theories, and their own ways to pair down and represent what they think is most essential about what's going on in the problem space.

Netlab

To state it simply, Netlab is built on the proposition that experimenters should be able to try out their own ideas, and not merely find new ways to use other people's ideas.

One very good way for a programmer to achieve such a goal in his design, is to reverse engineer the existing formulas. That is, for each existing formula, produce a simulation environment that would allow somebody to create the formula for the first time, were it not already known. This is one of the design philosophies underlying Netlab's software specification.

Some Practical Examples

To this point it has been a rather abstract post. What follows is mostly a list of links into the glossary (I think). Now that the I.P. protection is starting to come through, I'll be able to describe this stuff more openly, and more deeply. As new documentation becomes available I'll either try to update this section with links, or copy this section into a more complete discussion of the practical mechanisms provided for achieving the simple goal described above.

Chemicals
One of the abstractions provided by Netlab is the notion of chemicals. Neurons, beside producing output values on their axons based on a variety conditions (direct and indirect), are also capable of producing chemicals. The chemicals, much like the axon-level, can be specified to be produced in various concentration-levels based on a variety of environmental factors. The factors that lead to the production of a chemical are specified by the designer and can include stimulus on the neuron's synapses by other axons, other chemical influences in the vicinity of the neuron, or globally present chemicals (among many other factors). To specify a new chemical the designer simply comes up with a name for it.

No characteristics are explicitly specified for a given designer-named chemical. The properties and characteristics of any given named chemical are purely a biproduct of how other objects in the environment (usually other neurons) have been specified to respond/react to them. Responses to any given chemical can be different for different individual instances of a neuron, or for different classes of a neuron (this is simplified, "neuron" is really "object" and can include other super-types besides neurons),
Spacial and Temporal Distances
Netlab's description language provides a way to modularize the design and construction of neural networks. It allows experimenters to produce components, called "units", which contain other components, such as neurons and previously designed units.

The modular construct used to overcome complexity at design time, is preserved in the Netlab run-time, giving Netlab's networks an abstraction of volumetric space, which can be used as a framework when representing both spacial and temporal phenomena.
Pathfinding
Once you have a viable abstraction for representing temporal and volumetric chemical gradients, you can then begin to define all kinds of useful mechanisms based on the influence (e.g., repulsive or attractive) your chemical concentrations have on them. For example, like all neural network packages, Netlab includes the traditional Latent Connections. These are the static connections you determine at design time. Whether or not they actually develop is based on changes to their strengths, but the connection will always be between the same two neurons, which were specified at design time.

Netlab is able to go farther, allowing designers to specify Receptor Pads which are areas on a neuron's synapse-space that can make connections with any other neuron in the network while it is running. Other neurons put out something called a growth cone. Among other things, dynamic connections are facilitated at run time based on affinities or aversions to named chemicals specified for both the growth-cones, and the receptor pads. This allows, for example, a given class of growth cone to be defined to "desire", "seek-out", and "find" its perfect receptor pad, dynamically, as the network runs. It is good to mention again here, that chemicals influencing these movement decisions by growth-cones are also being produced dynamically, and their concentrations will be based on factors that are products of the running network within its dynamic environment.
No Limits On Feedback
A new patented learning method has been developed that completely eliminates past restrictions placed on types or amounts of feedback employed in the structure of the network. Beside just being great for general feedback that may want to span multiple local loops at times, this is also very nice for servo-structures, which put the outside world directly in the feedback path. This allows for representing the outside world as a the correction-factors that must be adapted, in order to correct for outside forces. In essence, the world's complex and chaotic stimuli become a transfer function that sits directly in the network's feedback loop. The network, then performs the function of correcting for inconsistencies in the feedback function, which it can then learn.

Brain Wiring Structure? How About a Donut?

nospam@example.com (John R) — Thu, 12 Aug 2010 12:29:00 -0700

A recent USC study applies a new technique that allows researches to more closely map the brain's wiring. One goal of the study is to better clarify our current understanding of the connection-structure of brains. Also, to try and settle the raging "It's an internetwork" / "It's a hierarchical pyramid" debate.

The Netlab abstraction is designed to facilitate a similar, but slightly different concept of brain wiring-structure, which is visually depicted in the cover art of the book:

Any Connectome You'd Like N^o 1

Netlab's idealized wiring-structure requirement (simplified)

The above diagram should be seen as a cross-section through a sphere, so the word "donut" in this entry-title takes some license. The interior/exterior connection-model, as depicted, does seem to find—at least passing— observational support in the USC study, e.g.,:

"The circuits showed up as patterns of circular loops, suggesting that at least in this part of the rat brain, the wiring diagram looks like a distributed network."

-djr