Feedback is very appreciated, send an email to email@example.com
How did intelligence come into existence? What are the properties that make humans smart? These questions have bothered me for a long while now, and I have tried to find my own answers and other perspectives in the field. One method to get a grip on intelligence is to follow what kind of methods the field of Reinforcement Learning is developing. This is essentially a bottom-up approach, aggregating all methods to see a pattern. I just recently published a huge mind map that tried to do just that. Other methods try to come up with principles from top-down and then test them or proof that these are optimal. Universal AI in the form of AIXI defines the theoretically optimal reinforcement agent while Active Inference is a physics and neuroscience inspired approach.
In this blog post I want to present my own, much simpler theory, summarized by a simple statement:
Any dynamical system that acts such that it keeps existing or replicating is more likely to be observed in the future.
For instance, any animal keeps regulating their body to survive and replicating for the continued existence of the species. Thus, you are more likely to observe a cat than a non-functioning cat. Both animals and species are dynamical systems. These dynamical systems can be recursive in the sense of one containing the other. One example is the recursion species -> animals -> organs -> cells -> physics. The dynamics of these are informed by the seed information (e.g. genetics), and (pseudo-)random1 perturbations from the environment. The lowest level in the recursion (i.e. physics) has fixed dynamics. Some of these perturbations are resisted by the dynamical system, others are not. For non-resisted perturbations, two cases can emerge. Firstly, if these perturbations are harmful, the dynamical system might cease to exist and thus also its replication capability. Secondly, if these perturbations are beneficial, the dynamical system might exist for prolonged periods of time or replicate such that another level of recursion is added on top.
At any time in a universe, the laws of this universe (i.e. the laws of physics) lead to random or pseudo-random interactions between entities. Most of this randomness will not lead to coherent systems (TODO, what is a coherent system? attractor state? but there is an additional optimization to extend the attractor state?). By chance, some of these interactions will be self-reinforcing and at some point replicating, from which perturbations create a wide variety of such dynamical systems. Because these variations compete for each other for resources, additional pressure for self-modification at any level in the recursive hierarchy is applied. This is reminiscent of evolutionary adaptation (On the Origin of Species).
The proposed principle does not talk about intelligence per se, but rather of the existence of any system (e.g. living being). Though, most living organisms are not perceived to be smart, but rather good at surviving in their niche. For instance, there are many more bacteria and viruses on this planet than humans. Thus, I am suggesting that intelligence is merely a side-effect of the existence/replication optimization objective in our universe (but a very powerful side-effect w.r.t. this optimization objective). For artificial machines that shall not just create complexity according to this objective but get increasingly better at solving a specific task or any computable task it will encounter in the future, we will need to define extrinsic or intrinsic objectives, for instance see Universal AI, POWERPLAY and other artificial curiosity based systems, or Empowerment.
Active inference is similar to this theory in the sense that any ‘living’ dynamical system optimizes to maintain certain attractor states by minimizing the free energy. This makes three assumptions, that we do not require: Firstly, we don’t assume ergodic behavior of the dynamical system, in the sense that states have to be revisited. Thus, we don’t have to define attractor states, but instead, any state that supports the existence of the system is permitted. Secondly, we don’t assume the minimization of a specific quantity for the internal dynamics of the system, like the free energy. Crucially, this theory includes reactive systems that do not model their environment but directly react to observed changes. As such, modeling the environment is not a prerequisite, but potentially useful.