People regularly make inferences about objects in the world that they cannot see by flexibly integrating information from multiple sources: auditory and visual cues, language, and our prior beliefs and knowledge about the scene. How are we able to so flexibly integrate many sources of information to make sense of the world around us, even if we have no direct knowledge? In this work, we propose a neurosymbolic model that uses neural networks to parse open-ended multi-modal inputs and then applies a Bayesian model to integrate different sources of information to evaluate different hypotheses. We evaluate our model with a novel object guessing game called "What's in the Box?" where humans and models watch a video clip of an experimenter shaking boxes and then try to guess the objects inside the boxes. Through a human experiment, we show that our model correlates strongly with human judgments, whereas unimodal ablated models and large multi-modal neural model baselines showed poor correlation.

To create usable and deployable Artificial Intelligence (AI) systems, there requires a level of assurance in performance under many different conditions. Many times, deployed machine learning systems will require more classic logic and reasoning performed through neurosymbolic programs jointly with artificial neural network sensing. While many prior works have examined the assurance of a single component of the system solely with either the neural network alone or entire enterprise systems, very few works have examined the assurance of integrated neurosymbolic systems. Within this work, we assess the assurance of end-to-end fully differentiable neurosymbolic systems that are an emerging method to create data-efficient and more interpretable models. We perform this investigation using Scallop, an end-to-end neurosymbolic library, across classification and reasoning tasks in both the image and audio domains. We assess assurance across adversarial robustness, calibration, user performance parity, and interpretability of solutions for catching misaligned solutions. We find end-to-end neurosymbolic methods present unique opportunities for assurance beyond their data efficiency through our empirical results but not across the board. We find that this class of neurosymbolic models has higher assurance in cases where arithmetic operations are defined and where there is high dimensionality to the input space, where fully neural counterparts struggle to learn robust reasoning operations. We identify the relationship between neurosymbolic models' interpretability to catch shortcuts that later result in increased adversarial vulnerability despite performance parity. Finally, we find that the promise of data efficiency is typically only in the case of class imbalanced reasoning problems.

In this study, we introduce application of Neurosymbolic Artificial Intelligence (NSAI) for predicting the impact strength of additive manufactured polylactic acid (PLA) components, representing the first-ever use of NSAI in the domain of additive manufacturing. The NSAI model amalgamates the advantages of neural networks and symbolic AI, offering a more robust and accurate prediction than traditional machine learning techniques. Experimental data was collected and synthetically augmented to 1000 data points, enhancing the model's precision. The Neurosymbolic model was developed using a neural network architecture comprising input, two hidden layers, and an output layer, followed by a decision tree regressor representing the symbolic component. The model's performance was benchmarked against a Simple Artificial Neural Network (ANN) model by assessing mean squared error (MSE) and R-squared (R2) values for both training and validation datasets. The results reveal that the Neurosymbolic model surpasses the Simple ANN model, attaining lower MSE and higher R2 values for both training and validation sets. This innovative application of the Neurosymbolic approach in estimating the impact strength of additive manufactured PLA components underscores its potential for optimizing the additive manufacturing process. Future research could investigate further refinements to the Neurosymbolic model, extend its application to other materials and additive manufacturing processes, and incorporate real-time monitoring and control for enhanced process optimization.