Prediction Tournament Paradox
In a prediction tournament, contestants ‘forecast’ by asserting a numerical probability for each of (say) 100 future real-world events. The scoring system is designed so that (regardless of the unknown true probabilities) more accurate forecasters will likely score better. This is true for one-on-one comparisons between contestants. But consider a realistic-size tournament with many contestants, with a range of accuracies. It may seem self-evident that the winner will likely be one of the most accurate forecasters. But, in the setting where the range extends to very accurate forecasters, simulations show this is mathematically false, within a somewhat plausible model. Even outside that setting the winner is less likely than intuition suggests to be one of the handful of best forecasters. Though implicit in recent technical papers, this paradox has apparently not been explicitly pointed out before, though is easily explained. It perhaps has implications for the ongoing IARPA-sponsored research programs involving forecasting. …

FastContext
Objective: To develop and evaluate FastContext, an efficient, scalable implementation of the ConText algorithm suitable for very large-scale clinical natural language processing. Background: The ConText algorithm performs with state-of-art accuracy in detecting the experiencer, negation status, and temporality of concept mentions in clinical narratives. However, the speed limitation of its current implementations hinders its use in big data processing. Methods: We developed FastContext through hashing the ConText’s rules, then compared its speed and accuracy with JavaConText and GeneralConText, two widely used Java implementations. Results: FastContext ran two orders of magnitude faster and was less decelerated by rule increase than the other two implementations used in this study for comparison. Additionally, FastContext consistently gained accuracy improvement as the rules increased (the desired outcome of adding new rules), while the other two implementations did not. Conclusions: FastContext is an efficient, scalable implementation of the popular ConText algorithm, suitable for natural language applications on very large clinical corpora. …

Visual Query Detection (VQD)
We propose Visual Query Detection (VQD), a new visual grounding task. In VQD, a system is guided by natural language to localize a \emph{variable} number of objects in an image. VQD is related to visual referring expression recognition, where the task is to localize only \emph{one} object. We describe the first dataset for VQD and we propose baseline algorithms that demonstrate the difficulty of the task compared to referring expression recognition. …

Fully Hyperbolic Convolutional Neural Networks
Convolutional Neural Networks (CNN) have recently seen tremendous success in various computer vision tasks. However, their application to problems with high dimensional input and output has been limited by two factors. First, in the training stage, it is necessary to store network activations for back propagation. Second, in the inference stage, a few copies of the image are typically stored to be concatenated to other network states deeper in the network. In these settings, the memory requirements associated with storing activations can exceed what is feasible with current hardware. For the problem of image classification, reversible architectures have been proposed that allow one to recalculate activations in the backwards pass instead of storing them, however, such networks do not perform well for problems such as segmentation. Furthermore, currently only block reversible networks have been possible because pooling operations are not reversible. Motivated by the propagation of signals over physical networks, that are governed by the hyperbolic Telegraph equation, in this work we introduce a fully conservative hyperbolic network for problems with high dimensional input and output. We introduce a coarsening operation that allows completely reversible CNNs by using the Discrete Wavelet Transform and its inverse to both coarsen and interpolate the network state and change the number of channels. This means that during training we do not need to store the activations from the forward pass, and can train arbitrarily deep or wide networks. Furthermore, our network has a much lower memory footprint for inference. We show that we are able to achieve results comparable to the state of the art in image classification, depth estimation, and semantic segmentation, with a much lower memory footprint. …