Search for: All records

Abstract The learning and recognition of object features from unregulated input has been a longstanding challenge for artificial intelligence systems. Brains, on the other hand, are adept at learning stable sensory representations given noisy observations, a capacity mediated by a cascade of signal conditioning steps informed by domain knowledge. The olfactory system, in particular, solves a source separation and denoising problem compounded by concentration variability, environmental interference, and unpredictably correlated sensor affinities using a plastic network that requires statistically well-behaved input. We present a data-blind neuromorphic signal conditioning strategy, based on the biological system architecture, that normalizes and quantizes analog data into spike-phase representations, thereby transforming uncontrolled sensory input into a regular form with minimal information loss. Normalized input is delivered to a column of spiking principal neurons via heterogeneous synaptic weights; this gain diversification strategy regularizes neuronal utilization, yoking total activity to the network’s operating range and rendering internal representations robust to uncontrolled open-set stimulus variance. To dynamically optimize resource utilization while balancing activity regularization and resolution, we supplement this mechanism with a data-aware calibration strategy in which the range and density of the quantization weights adapt to accumulated input statistics. 

The goal of odor source separation and identification from real-world data presents a challenging problem. Both individual odors of potential interest and multisource odor scenes constitute linear combinations of analytes present at different concentrations. The mixing of these analytes can exert nonlinear and even nonmonotonic effects on cross-responsive chemosensors, effectively occluding diagnostic activity patterns across the array. Neuromorphic algorithms, inspired by specific computational strategies of the mammalian olfactory system, have been trained to rapidly learn and reconstruct arbitrary odor source signatures in the presence of background interference. However, such networks perform best when tuned to the statistics of well-behaved inputs, normalized and predictable in their activity distributions. Deployment of chemosensor arrays in the wild exposes these networks to disruptive effects that exceed these tolerances. To address the problems inherent to chemosensory signal conditioning and representation learning, the olfactory bulb deploys an array of strategies: (1) shunting inhibition in the glomerular layer implements divisive normalization, contributing to concentration-invariant representations; (2) feedforward gain diversification (synaptic weight heterogeneity) regularizes spiking activity in the external plexiform layer (mitral and granule cells), enabling the network to handle unregulated inputs; (3) gamma-band oscillations segment activity into packets, enabling a spike phase code and iterative denoising; (4) excitatory and inhibitory spike timing dependent learning rules induce hierarchical attraction basins, enabling the network to map its highly complex inputs to regions of a lower dimensional manifold; (5) neurogenesis in the granule cell layer enables lifelong learning and prevents order effects (regularizing the learned synaptic weight distribution over the span of training). Here, we integrate these motifs into a single neuromorphic model, bringing together prior OB-inspired model architectures. In a series of simulation experiments including real-world data from a chemosensor array, we demonstrate the network’s ability to learn and detect complex odorants in variable environments despite unpredictable noise distributions. 

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.