Babak Bagheri

We know very little about how our brains work. Only recently have we begun to learn what goes on inside the cells and connections that make up the brain. These are good first steps, but the real challenge is to understand the network effects that actually lead to behaviors and how these network arrangements are formed. One group made a splash recently by claiming to have simulated the brain of a cat on a computer. This heroic computational effort needed one of the largest and fastest multi-processing computers on the planet. Even so, the simulation was limited and abstracted away from the real cat brain.

The RoBoard RB-100, a nano-itx board

Given this state of relative ignorance, can one take a practical engineering approach to construct an “artificial brain?” My contention is that this is possible. We need to combine insights from what little we know about the brain and complex computation in general. To these insights we should add something like the Nike tag line: “Just do it.” Fortunately, off-the-shelf processors are now powerful enough and networks are fast enough that we are less constrained by computational power than ever before. The key, as has been pointed out here before, is to avoid direct simulation of biological brains and think creatively about  computational kernels and network arrangements that can learn.

Engineering efforts of this kind will not only have direct benefits, but they will also enhance our understanding of biological systems. We should keep in mind though that these are only first steps. Ray Kurzweil’s singularity will not suddenly materialize tomorrow.

Network effects had been neglected for quite a long time. The classical “reductionist” view of the world was simply this: if we understand the rules that govern the pieces of the universe, then we can easily deduce large-scale behaviors. The past century has shown that this is wishful thinking at best.

Much has now been said about the level of complexity that interconnections among simple components introduce. This appreciation for network effects has not yet been exploited for engineering purposes fully. The old reductionist views still dominate in most engineering disciplines. The same is true about other practical arts; we do not yet have good ways of purposefully exploiting network-introduced complexity.

The reasons for this neglect are deep. To exploit the kind of complexity that network connections bring about we need to look at design differently. We need to view design as guidance instead of control. Complex systems do not respond well to direct control; they can, however, be guided and steered. We know very little about techniques to do this kind of guidance and control effectively.

Japanese Zen Garden (National Geographic)

There is one group, though, that has been struggling with these methods for some time: teachers and trainers. Living systems, especially people and groups of people, present exactly the kind of complexity that requires guidance and steering. Unfortunately, the track record for teaching and training is not stellar.

Perhaps the most effective of trainers have been spiritual teachers, for example Zen masters. Zen spiritual leaders have instinctively understood that guiding a complex mind requires meticulous attention to the environment. These environments are arranged to evoke the proper frames of mind that encourage the right mental changes.

We should start thinking of the machines we build as potential trainees and students. Our task is to design into them the kind of complexity that can be guided as we need. If a machine is simple enough to be controlled directly (“programmed”), then it’s probably too simple to do anything really interesting.

Software-controlled machines have been around for some time now. But we’re nowhere near a world filled with robotic helpers. There are deep reasons for this. One important reason is this: we’ve been using the wrong approach to program the machines.

Techniques for programming robots have an odd quality about them: the software contains numerical methods combined with symbolic heuristic methods. The numerical methods are essentially those used in computational physics. The symbolic methods are essentially those used to analyze symbolic phenomena like language and “mental processes”. Both sets of methods are analytical in nature. They are invaluable in understanding the world, and that understanding is very useful in creating robotic software. But I believe it is a mistake to use the methods directly.

A Neural Network

Let’s see what a different approach may look like. There is one set of relevant methods that is synthetic in nature: these are “computational kernel” methods. The set includes cellular automata and fractals. Ironically, these synthetic techniques are often proposed for analyzing physical phenomena. They may be useful analysis, or even paradigm-changing as some claim. But they are much more promising as a basis for robotic software.

To control a machine, we do not need to program into it sophisticated techniques for understanding how machines work. We just need to provide the right computational kernels that, in aggregate, lead to sophisticated behavior. This kind of approach has been seriously attempted only by “neural network” (and their close cousins “probabilistic graphs”, “bayes nets”, etc.) researchers and practitioners . Unfortunately, neural networks have suffered from the analysis-synthesis confusion as well; they have been constrained by the analytical need to model biological brains.

It’s time to get beyond this confusion and design synthetic techniques that learn the behaviors we want. We can then use analytical techniques to understand why the systems we create behave the way they do. But that analysis will be separate from the computational kernels we use to program them.

Are experiments the only way to navigate the bootstrap process? Are there no rational shortcuts? The answer, as usual, is “yes, but.” The alternate or complementary approach is what I call “social imagination:” the ability to imagine the effect an enterprising act will have on a group. This is really an exercise in imagination, not calculation. We don’t have any formulas to compute what the effect of any act will be on a complex social environment. But we humans seem to be endowed with brains that can imagine various social outcomes in uncanny ways.

Adult-Born Neurons (Veronica Piatti et. al.)

Recently, there have been a number of publications and discussions about these human abilities. They all point out that our social imagination is related to the constituents of our brains and how they are wired, or, more accurately, continuously rewired.

Social imagination seems to be built into us in ways that we’re just beginning to understand. A very dramatic example of these abilities is attributed to the “mirror neuron system” of the brain. The system, discovered by accident in an Italian laboratory, allows us to copy the brain state of another person by mere observation.

Apparently, our abilities go beyond mirroring: we can play out scenarios of what people will think. There are, most likely, severe limitations here. I don’t believe we have social crystal balls built into our brains. It’s also most likely that people differ a great deal in their capacity for social imagination like they differ in every other capability.

To complement actual experiments, then, we’re well advised to carry out “thought experiments” to see what the possible outcomes may be. These imaginative musings should be guides for framing the actual experiments and hopefully they will increase the probability of success. As with all other mental abilities, social imagination will improve with practice; so the more we do this the better we’ll be. Hence the value of experience.