More Like this

1. WACV 2022

   Matt Gorbett, Nathaniel Blanchard (January 2022, Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2022, pp. 34-43)

   Neural networks are vulnerable to a wide range of erroneous inputs such as corrupted, out-of-distribution, misclassified, and adversarial examples. Previously, separate solutions have been proposed for each of these faulty data types, however, in this work we show that a collective set of inputs with variegated data quality issues can be jointly identified with a single model. Specifically, we train a linear SVM classifier to detect four types of erroneous data using the hidden and softmax feature vectors of pre-trained neural networks. Our results indicate that these faulty data types generally exhibit linearly separable activation properties from correctly processed examples. We are able to identify erroneous inputs with an AUROC of 0.973 on CIFAR10, 0.957 on Tiny ImageNet, and 0.941 on ImageNet. We experimentally validate our findings across a diverse range of datasets, domains, and pre-trained models. 

   more » « less
2. Deep learning optimization for small object classification in lensfree holographic microscopy

   https://doi.org/10.1364/OE.527353  

   Potter, Colin_J; Sreevatsan, Shriniketh; McLeod, Euan (September 2024, Optics Express)

   Lensfree holographic microscopy is a compact and cost-effective modality for imaging large fields of view with high resolution. When combined with automated image processing, it can be used for biomolecular sensing where biochemically functionalized micro- and nano-beads are used to label biomolecules of interest. Neural networks for image feature classification provide faster and more robust sensing results than traditional image processing approaches. While neural networks have been widely applied to other types of image classification problems, and even image reconstruction in lensfree holographic microscopy, it is unclear what type of network architecture performs best for the types of small object image classification problems involved in holographic-based sensors. Here, we apply a shallow convolutional neural network to this task, and thoroughly investigate how different layers and hyperparameters affect network performance. Layers include dropout, convolutional, normalization, pooling, and activation. Hyperparameters include dropout fraction, filter number and size, stride, and padding. We ultimately achieve a network accuracy of ∼83%, and find that the choice of activation layer is most important for maximizing accuracy. We hope that these results can be helpful for researchers developing neural networks for similar classification tasks. 

   more » « less
3. Fairness of Information Flow in Social Networks

   https://doi.org/10.1145/3578268  

   Jalali, Zeinab S.; Chen, Qilan; Srikanta, Shwetha M.; Wang, Weixiang; Kim, Myunghwan; Raghavan, Hema; Soundarajan, Sucheta (December 2023, ACM Transactions on Knowledge Discovery from Data)

   Social networks form a major parts of people’s lives, and individuals often make important life decisions based on information that spreads through these networks. For this reason, it is important to know whether individuals from different protected groups have equal access to information flowing through a network. In this article, we define the Information Unfairness (IUF) metric, which quantifies inequality in access to information across protected groups. We then introduce MinIUF , an algorithm for reducing inequalities in information flow by adding edges to the network. Finally, we provide an in-depth analysis of information flow with respect to an attribute of interest, such as gender, across different types of networks to evaluate whether the structure of these networks allows groups to equally access information flowing in the network. Moreover, we investigate the causes of unfairness in such networks and how it can be improved. 

   more » « less
4. Representations of syntax [MASK] useful: Effects of constituency and dependency structure in recursive LSTMs

   Lepori, Michael; Linzen, Tal; McCoy, R. Thomas (July 2020, Association for Computational Linguistics)

   Sequence-based neural networks show significant sensitivity to syntactic structure, but they still perform less well on syntactic tasks than tree-based networks. Such tree-based networks can be provided with a constituency parse, a dependency parse, or both. We evaluate which of these two representational schemes more effectively introduces biases for syntactic structure that increase performance on the subject-verb agreement prediction task. We find that a constituency-based network generalizes more robustly than a dependency-based one, and that combining the two types of structure does not yield further improvement. Finally, we show that the syntactic robustness of sequential models can be substantially improved by fine-tuning on a small amount of constructed data, suggesting that data augmentation is a viable alternative to explicit constituency structure for imparting the syntactic biases that sequential models are lacking. 

   more » « less
5. Diversity of Emergent Dynamics in Competitive Threshold-Linear Networks

   https://doi.org/10.1137/22M1541666  

   Morrison, Katherine; Degeratu, Anda; Itskov, Vladimir; Curto, Carina (March 2024, SIAM Journal on Applied Dynamical Systems)

   Threshold-linear networks consist of simple units interacting in the presence of a threshold nonlinearity. Competitive threshold-linear networks have long been known to exhibit multistability, where the activity of the network settles into one of potentially many steady states. In this work, we find conditions that guarantee the absence of steady states, while maintaining bounded activity. These conditions lead us to define a combinatorial family of competitive threshold-linear networks, parametrized by a simple directed graph. By exploring this family, we discover that threshold-linear networks are capable of displaying a surprisingly rich variety of nonlinear dynamics, including limit cycles, quasi-periodic attractors, and chaos. In particular, several types of nonlinear behaviors can co-exist in the same network. Our mathematical results also enable us to engineer networks with multiple dynamic patterns. Taken together, these theoretical and computational findings suggest that threshold-linear networks may be a valuable tool for understanding the relationship between network connectivity and emergent dynamics. 

   more » « less