The DIAMOND Model: Deep Recurrent Neural Networks for Self-Organizing Robot Control.

The proposed architecture applies the principle of predictive coding and deep learning in a brain-inspired approach to robotic sensorimotor control. It is composed of many layers each of which is a recurrent network. The component networks can be spontaneously active due to the homeokinetic learning rule, a principle that has been studied previously for the purpose of self-organized generation of behavior. We present robotic simulations that illustrate the function of the network and show evidence that deeper networks enable more complex exploratory behavior.

Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop.

Active inference is an ambitious theory that treats perception, inference, and action selection of autonomous agents under the heading of a single principle. It suggests biologically plausible explanations for many cognitive phenomena, including consciousness. In active inference, action selection is driven by an objective function that evaluates possible future actions with respect to current, inferred beliefs about the world. Active inference at its core is independent from extrinsic rewards, resulting in a high level of robustness across e.g., different environments or agent morphologies. In the literature, paradigms that share this independence have been summarized under the notion of intrinsic motivations. In general and in contrast to active inference, these models of motivation come without a commitment to particular inference and action selection mechanisms. In this article, we study if the inference and action selection machinery of active inference can also be used by alternatives to the originally included intrinsic motivation. The perception-action loop explicitly relates inference and action selection to the environment and agent memory, and is consequently used as foundation for our analysis. We reconstruct the active inference approach, locate the original formulation within, and show how alternative intrinsic motivations can be used while keeping many of the original features intact. Furthermore, we illustrate the connection to universal reinforcement learning by means of our formalism. Active inference research may profit from comparisons of the dynamics induced by alternative intrinsic motivations. Research on intrinsic motivations may profit from an additional way to implement intrinsically motivated agents that also share the biological plausibility of active inference.

Health effects classification and its role in the derivation of minimal risk levels: developmental effects.

Agency for Toxic Substances and Disease Registry (ATSDR) utilizes chemical-specific minimal risk levels (MRLs) to assist in evaluating the public health risk associated with exposure to hazardous substances. The MRLs are derived based on the health effects data compiled from current literature searches and presented in ATSDR's toxicological profiles. Health effects are categorized according to their degree of severity (e.g., serious, less serious, minimal, and not adverse). This evaluation is important, because each respective category can be assigned a different amount of uncertainty, thus affecting the final value of the calculated MRL. From the total of 272 MRLs derived as of December 1997, 21 were based on developmental effects. ATSDR's ranking of developmental health effects as described in the Guidance for Developing Toxicological Profiles and specific examples of how the categorized health effects were used in MRL derivations are provided in this paper.