So the basic concept behind artificial neural networks is to have a graph with input and output nodes. You send logic through the graph, as a series of pipes. The logic within the graph (each node serves as I/O) processes the input values and provides output values based on the graph structure. You create the graph by training/conditioning the neural network - thus creating the logic.<p>What would come of applying this theory to social networks (and other occurrences of graph patterns throughout the internet)?<p>The reason that neural networking works is that the structures in the graph fundamentally represent patterns outside of the graph; effectively their logic mimics external mathematical patterns - they are a simplification of the information that the network digests as it is conditioned.<p>Extrapolating from this fact, shouldn't the patterns (and hence the logic) within social networks hold meaning? What would be the equivalent of running "pulses" through the social graph?<p>There would be two ways to do this.<p>1. Internally - create a simple algorithm that uses the logic held in the social graph to process inputs and outputs. For example, you might send an array of integers through a subgraph of Faceboook and get some other integers out from different end nodes within the subgraph. (With internal graph processing, you'd need access to the database, so only the social network would have the ability to run analytics like this.)<p>2. Externally - literally send a piece of information (an email that get's forwarded from one person (node) to the next, a tweet retweeted, or a hyperlink referenced) through the social work and follow it's path through the network. It's ending point would effectively be a function of it's starting point, and it's ending quality (for example, if the email was somehow changed by the end), would also be a function of it's starting point.<p>What could be made of such analytics? Are people already doing this? (I assume they are... I can't be the first one who thought of this.)<p>Btw, this is only my second post, so looking forward to getting familiar with the hacker community and hello. Let me know if this post was too long to be enjoyable.
Disclaimer: I'm not an expert on this, although I have been doing a lot of reading / studying on social network analysis and network science lately. But just to throw some ideas out and provide some food for thought:<p><i>Extrapolating from this fact, shouldn't the patterns (and hence the logic) within social networks hold meaning?</i><p>Probably, yeah.<p><i>What would be the equivalent of running "pulses" through the social graph?</i><p>Depends on how you see the analogy. Research on "diffusion of innovations"[1] could relate to this... the idea being that the introduction of a new "thing" (a technology innovation) is your "pulse" and its spread through the network is the analogue of the neural network processing. Also possibly related would be the idea of "information cascades" in networks[2]. Seems like there's something of a parallel between some of the SNA / Network Theory stuff and the Spreading Activation[3] stuff as well.<p>I don't know about trying to treat the social network as an analogue of a neural network, but the Social Network Analysis[4] folks certainly study the flow of information through a network. You might poke around the journals and forums on that, or the Network Science[5] and/or Complex Adaptive Systems[6] people and see if anybody is doing anything related.<p>[1]: <a href="http://en.wikipedia.org/wiki/Diffusion_of_innovations" rel="nofollow">http://en.wikipedia.org/wiki/Diffusion_of_innovations</a><p>[2]: <a href="http://en.wikipedia.org/wiki/Information_cascade" rel="nofollow">http://en.wikipedia.org/wiki/Information_cascade</a><p>[3]: <a href="http://en.wikipedia.org/wiki/Spreading_activation" rel="nofollow">http://en.wikipedia.org/wiki/Spreading_activation</a><p>[4]: <a href="http://en.wikipedia.org/wiki/Social_network#Social_network_analysis" rel="nofollow">http://en.wikipedia.org/wiki/Social_network#Social_network_a...</a><p>[5]: <a href="http://en.wikipedia.org/wiki/Network_theory" rel="nofollow">http://en.wikipedia.org/wiki/Network_theory</a><p>[6]: <a href="http://en.wikipedia.org/wiki/Complex_adaptive_system" rel="nofollow">http://en.wikipedia.org/wiki/Complex_adaptive_system</a><p>There's an interesting wiki full of links related to network science and complex systems here: <a href="http://netwiki.amath.unc.edu/" rel="nofollow">http://netwiki.amath.unc.edu/</a> that might be fun to explore.
I'm by no means an expert, but I think you're confused as to how NNs work.<p>>Extrapolating from this fact, shouldn't the patterns (and hence the logic) within social networks hold meaning?<p>Most likely not. Neural nets are trained to map relations between inputs and outputs. The way that each neuron relates to the others is set, during training, so that when you present a given input to the network, you get something close to the expected output. In a social network, you basically just have a (somehow weighted) graph of people, but you lack the means to "train" it. If you somehow found a way to use the social graph as a pre-trained neural net, you'd most likely get the old "garbage in - garbage out".<p>Also, what kind of inputs and outputs would you expect to use?<p>I think you'd be better off thinking of ways to exploit the social graph just as a graph (if you could have access to it, that is).