Topic

Suppose that many of the decisions we and other animals make are fundamentally non-deterministic. Suppose, that is, that the mechanisms in our nervous systems making the decisions are irreducibly stochastic: no amount of information about the structure of a nervous system, its components, its past history, its current sensory inputs, etc., would allow us to predict the outcome of a decision more definitely than a collection of probabilities.

Suppose further that the decision-making apparatus is a network of simple but inter-communicating stochastic decision-making parts. Can we imagine and define such a part that is simple enough to be understandable, but complex enough to embody the essence of stochastic decision making? Can these parts be interconnected into complex networks capable of doing complicated things? Can we understand what such networks do? Can we describe precisely what they do mathematically? Can we design such networks to behave in ways that we specify? Can we learn anything about real, living neural networks by studying networks of these simple parts?

Finding answers to these questions is the subject matter of this tutorial. We will find that we can, indeed, answer all of these questions affirmatively - while, at the same time, developing a very powerful and mathematically rigorous body of theoretical concepts.


Objective and Intended Audience

The objective of this tutorial is to give participants enough information about networks of stochastic artificial neurons that they can apply the concepts to their own work and even build upon these concepts and extend them further.

This tutorial is expected to be of interest to:
  • researchers working with ANN models that incorporate stochastic decision-making elements,
  • researchers working with deterministic ANN models but looking for more powerful methods of designing and analyzing such models,
  • researchers working with ANN models that operate in nondeterministic environments,
  • biologists interested in developing models of nondeterministic behaviors in animals (such as random walks), and
  • researchers interested in developing the connections between stochastic ANN models and other fields such as Game Theory and Information Theory.

Description

We will begin by reviewing key concepts from discrete probability theory: the concept of a trial, the concept of a sample space, and the concept of a measure. We will highlight the key role that time plays in these concepts, a role that can often be safely ignored when dealing with deterministic systems. We will emphasize the fact that any theory dealing with stochastic ANNs has to be supported by a mathematical formalism that allows both sample spaces and measures to be manipulated at the same time.


Next, we will define the notion of a stochastic artificial neuron (SAN). We will formalize the abstract concept of a SAN with a formal definition. This will require that we introduce a mathematical description that precisely abstracts the decision-making behavior of the SAN.


This mathematical description is a stochastic matrix which we will call a Stochastic Neural Function (SNF). We will note that a SNF, in the form of a matrix, contains information about sample spaces in the positions of its elements and measures in the actual numbers.


Next, we will consider feed-forward (FF) networks of SANs. Here again, we have to pay careful attention to time. We will introduce a formal definition of a FF network that involves a layered structure with the decisions of individual SANs being made in sequence through the layers. Feed-forward means that the inputs to a SAN in the network can come only from the inputs to the entire network or from the outputs of SANs in previous layers of the network. We will note that there is a SNF in the form of a stochastic matrix that describes the behavior of the entire network.


At this point, we will address the question: if we know the structure of a FF network and the SNFs describing its individual SANs, what does the whole network do? That is, what is the SNF that describes the entire network? Informal, ad hoc methods can be used to attack this question when networks are simple or have structures that make analysis easy. But we need a method that gives an answer in any and all cases. This is the topic we take up next.


This is a large topic. It will require us to develop the algebra of stochastic matrices in some new ways and it will require us to introduce some new, but very useful concepts. We will find that the algebra of stochastic matrices is very powerful: it allows us to manipulate sample spaces and measures at the same time; it allows us to describe networks that have one output and networks that have more than one output; it allows us to deal seamlessly with networks that are a mixture of deterministic and stochastic ANs; it allows us to deal seamlessly with stochastic (or deterministic) networks interacting with stochastic (or deterministic) environments, and; it allows us to deal seamlessly with networks that have no inputs, i.e., information sources, and with networks that have no outputs, i.e., information sinks.


Next, we will address the question: if we can specify what we want a FF network to do, can we design a network that meets this specification? Again, informal, ad hoc methods can be used if the SNF is simple or is structured in ways that make synthesis easy. But we also need methods that will always work for any SNF. Here, we will discuss several methods that are generalized from deterministic switching theory. We will include methods that can be used for networks with a single output and methods that can be used when more than one output is called for. We will find that there are many networks that can realize any given SNF. And we will highlight several significant insights, such as the fact that it is always possible, given any SNF, to find a network that realizes that SNF that consists of a purely deterministic network with some inputs that are from simple information sources.


At this point, we will be ready to address the subject of recurrent networks. These are networks that have one or more SANs whose outputs loop back to become inputs to SANs in earlier layers of the network. Recurrent networks have the ability to store information in "internal states". This means that previous inputs, previous outputs, and/or previous internal states can influence the current output decisions of recurrent networks, not just current inputs, as is the case for FF networks. We will precisely define what we mean by a recurrent network and then we will discuss two key results. The first is that any recurrent network is always equivalent to a FF network with some outputs of the entire network fed back as inputs to the entire network. This reduces the analysis of a recurrent network to the analysis of a FF network. The second key result is that if we know what we want a recurrent network to do, we can always describe the problem as a FF network with some outputs fed back as inputs. So we can always turn the problem of synthesizing a recurrent network into a problem of synthesizing a FF network.


As an example of how we can apply the concepts outlined above to model the observed behavior of a biological system, we will next discuss the distributions of step lengths in the random walks of foraging animals. Experimental data indicate that the step lengths in the random walks of animals often fall into one of two patterns: an exponential distribution of step lengths or a Lévy distribution of step lengths, the latter with a long-step-length tail that appears to be exponential.


We will find that for each of these distributions, there are simple stochastic ANNs that can make decisions that mimic the observed behavior. We will find that a single neuron, acting as an information source, can produce the decisions leading to an exponential distribution of step lengths. We will find that a simple recurrent network can make the decisions leading to a Lévy distribution. We will find that Markov chains provide a useful paradigm for describing mathematically the behavior of recurrent stochastic ANNs. Using these models, we will find that we are able to make significant inferences about the underlying neural structures of the animals while at the same time uncovering possible explanations for details of the observed behaviors that are otherwise puzzling. In addition, these models make predictions about other characteristics of the foraging behavior that can be used to suggest future experiments.


We will conclude with an overview of the broader context within which to understand networks of SANs. We will emphasize how such models inter-work smoothly and naturally with other well-established areas of knowledge, filling gaps in them and linking them together. Some of these areas are, by definition, non-deterministic, such as information theory, game theory, and the theory of stochastic automata. Some are deterministic, such as switching theory and deterministic automata theory. We will also note some of the connections with deterministic ANN theory, particularly threshold logic and adaptive threshold logic.


Presenter

Richard C. (Dick) Windecker received his Ph.D. in experimental solid state physics from the University of Illinois at Urbana-Champaign. He retired from Bell Labs (Alcatel-Lucent). In between, he taught university physics at the advanced undergraduate level, he did research in the area of stochastic ANNs, he was a systems engineer, and he was a manager of systems engineers. Currently, he is continuing to do research in the area of stochastic ANNs. He may be contacted at or +1 732 233-0838.

© 2011 rcwindecker.com, Richard C. Windecker
Site built and hosted at EPFVP