Loligo Blog

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 becomes 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. . .

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.

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 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.





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.

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.






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.






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.

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. ”

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.

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.





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.





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.





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.