We address the challenge of inferring the design intentions of a human by an intelligent virtual agent that collaborates with the human. First, we propose a dynamic Bayesian network model that relates design intentions, objectives, and solutions during a human's exploration of a problem space. We then train the model on design behaviors generated by a search agent and use the model parameters to infer the design intentions in a test set of real human behaviors. We find that our model is able to infer the exact intentions across three objectives associated with a sequence of design outcomes 31.3% of the time. Inference accuracy is 50.9% for the top two predictions and 67.2% for the top three predictions. For any singular intention over an objective, the model's mean F1-score is 0.719. This provides a reasonable foundation for an intelligent virtual agent to infer design intentions purely from design outcomes toward establishing joint intentions with a human designer. These results also shed light on the potential benefits and pitfalls in using simulated data to train a model for human design intentions. CCS CONCEPTS • Human-centered computing → Human computer interaction (HCI).

In the mammalian olfactory bulb (OB), gamma oscillations in the local field potential are generated endogenously during odor sampling. Such oscillations arise from dynamical systems that generate organized periodic behavior in neural circuits, and correspond to spike timing constraints at fine timescales. While the cellular and network mechanisms of gamma oscillogenesis in the OB are reasonably well established, it remains unclear how these fine-timescale dynamics serve to represent odors. Are patterns of spike synchrony on the gamma timescale replicable and odor-specific? Does the transformation to a spike-timing metric embed additional computations? To address these questions, we used OB slices to examine the spike timing dynamics evoked by "fictive odorants" generated via spatiotemporally patterned optogenetic stimulation of olfactory sensory neuron axonal arbors. We found that a small proportion of mitral/tufted cells phase-lock strongly to the fast oscillations evoked by fictive odorants, and exhibit tightly coupled spike-spike synchrony on the gamma timescale during this stimulation. Moreover, the specific population of synchronized neurons differed based on the "quality", but not the "concentration", of the fictive odorant presented, and was conserved across multiple presentations of the same fictive odorant. Given the established selectivity of piriform cortical pyramidal neurons for inputs synchronized on this timescale, we conclude that spike synchronization on a milliseconds timescale is a metric by which the OB encodes and exports afferent odor information in a concentration-invariant manner. As a corollary, mitral/tufted cell spikes that are not organized in time may not contribute effectively to the ensemble odor representation.