Approaching Artificial Intelligence as an Embodied Developmental Process

<div>In this submission, we will lay out an argument for building artificial intelligence (AI) based on biological development. A developmental AI consists of three components: an embodied input/output network, a critical period for information acquisition and connectivity, and a network topology that expands over time according to the principles of contingency and developmental freedom.</div><div><br></div><div>Developmental contingency restricts the developmental neural network to an increasingly limited set of possible trajectories. While contingency results in earlier</div><div>developmental events (cell differentiation) to constrain the range of possibilities for future developmental events (formation of a network motif), developmental freedom</div><div>is the tendency for information and representations in particular to take advantage of a stable underlying topology. This contributes to an artificial brain that acts as a</div><div>generative network with a further capacity for behavioral complexity. </div><div><br></div><div>We will demonstrate examples for each of these points using developmental Braitenberg Vehicles (dBVs) as the subject of thought experiments. These thought experiments will take the form of a contingency analysis of a typical dBV input/output network topology. This analysis shows how embodiment developmental agents provide three potentially powerful mechanisms for the emergence of adaptive</div><div>intelligent systems. First, the presence of an embodied input/output network can act to structure input data. Secondly, the existence of a critical period embedded within the developmental process acts to structure association-building through network complexity. Finally, developmental freedom results from the placement of the critical</div><div>period within a sequence of events defining the biological developmental process, which in turn can enhance both information acquisition and network structure. In</div><div>conclusion, we will discuss potential benchmarks and future advances in the developmental approach, including the application of epigenetic landscapes to characterize the formation of a neural network topology.</div>