Visual question answering requires high-order reasoning about an image, which is a fundamental capability needed by machine systems to follow complex directives. Recently, modular networks have been shown to be an effective framework for performing visual reasoning tasks. While modular networks were initially designed with a degree of model transparency, their performance on complex visual reasoning benchmarks was lacking. Current state-of-the-art approaches do not provide an effective mechanism for understanding the reasoning process. In this paper, we close the performance gap between interpretable models and state-of-the-art visual reasoning methods. We propose a set of visual-reasoning primitives which, when composed, manifest as a model capable of performing complex reasoning tasks in an explicitly-interpretable manner. The fidelity and interpretability of the primitives' outputs enable an unparalleled ability to diagnose the strengths and weaknesses of the resulting model. Critically, we show that these primitives are highly performant, achieving state-of-the-art accuracy of 99.1% on the CLEVR dataset. We also show that our model is able to effectively learn generalized representations when provided a small amount of data containing novel object attributes. Using the CoGenT generalization task, we show more than a 20 percentage point improvement over the current state of the art.

In this paper we investigate the problem of localizing a mobile device based on readings from its sensors utilizing machine learning methodologies. We consider a real-world environment, collect a dense set of 3110 datapoints, and examine the performance of a substantial number of machine learning algorithms. We found algorithms that have a mean error as accurate as 0.76 meters, outperforming other indoor localization systems. We also propose a hybrid instance-based approach that results in a speed increase by a factor of ten with no loss of accuracy in a live deployment over standard instance-based methods. Further, we determine how less dense datasets affect accuracy, important for use in real-world environments. Finally, we demonstrate that these approaches are appropriate for real-world deployment by evaluating their performance in an online, in-motion experiment. The Learning Based Indoor Positioning System (LIPS) Android application source has been made available on the web.