Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

Improving Neural Network Robustness through Neighborhood Preserving Layers

Jan 29, 2021
Bingyuan Liu, Christopher Malon, Lingzhou Xue, Erik Kruus

Robustness against adversarial attack in neural networks is an important research topic in the machine learning community. We observe one major source of vulnerability of neural nets is from overparameterized fully-connected layers. In this paper, we propose a new neighborhood preserving layer which can replace these fully connected layers to improve the network robustness. We demonstrate a novel neural network architecture which can incorporate such layers and also can be trained efficiently. We theoretically prove that our models are more robust against distortion because they effectively control the magnitude of gradients. Finally, we empirically show that our designed network architecture is more robust against state-of-art gradient descent based attacks, such as a PGD attack on the benchmark datasets MNIST and CIFAR10.

* An earlier short version of this paper without proof is presented in 25th International Conference on Pattern Recognition(ICPR), Manifold Learning from Euclid to Riemann workshop 

  Access Paper or Ask Questions

Analyzing Gender Bias within Narrative Tropes

Oct 30, 2020
Dhruvil Gala, Mohammad Omar Khursheed, Hannah Lerner, Brendan O'Connor, Mohit Iyyer

Popular media reflects and reinforces societal biases through the use of tropes, which are narrative elements, such as archetypal characters and plot arcs, that occur frequently across media. In this paper, we specifically investigate gender bias within a large collection of tropes. To enable our study, we crawl tvtropes.org, an online user-created repository that contains 30K tropes associated with 1.9M examples of their occurrences across film, television, and literature. We automatically score the "genderedness" of each trope in our TVTROPES dataset, which enables an analysis of (1) highly-gendered topics within tropes, (2) the relationship between gender bias and popular reception, and (3) how the gender of a work's creator correlates with the types of tropes that they use.


  Access Paper or Ask Questions

Efficient Pedestrian Detection in Top-View Fisheye Images Using Compositions of Perspective View Patches

Sep 06, 2020
Sheng-Ho Chiang, Tsaipei Wang

Pedestrian detection in images is a topic that has been studied extensively, but existing detectors designed for perspective images do not perform as successfully on images taken with top-view fisheye cameras, mainly due to the orientation variation of people in such images. In our proposed approach, several perspective views are generated from a fisheye image and then concatenated to form a composite image. As pedestrians in this composite image are more likely to be upright, existing detectors designed and trained for perspective images can be applied directly without additional training. We also describe a new method of mapping detection bounding boxes from the perspective views to the fisheye frame. The detection performance on several public datasets compare favorably with state-of-the-art results.


  Access Paper or Ask Questions

Solving the functional Eigen-Problem using Neural Networks

Jul 20, 2020
Ido Ben-Shaul, Leah Bar, Nir Sochen

In this work, we explore the ability of NN (Neural Networks) to serve as a tool for finding eigen-pairs of ordinary differential equations. The question we aime to address is whether, given a self-adjoint operator, we can learn what are the eigenfunctions, and their matching eigenvalues. The topic of solving the eigen-problem is widely discussed in Image Processing, as many image processing algorithms can be thought of as such operators. We suggest an alternative to numeric methods of finding eigenpairs, which may potentially be more robust and have the ability to solve more complex problems. In this work, we focus on simple problems for which the analytical solution is known. This way, we are able to make initial steps in discovering the capabilities and shortcomings of DNN (Deep Neural Networks) in the given setting.


  Access Paper or Ask Questions

Model Fusion with Kullback--Leibler Divergence

Jul 13, 2020
Sebastian Claici, Mikhail Yurochkin, Soumya Ghosh, Justin Solomon

We propose a method to fuse posterior distributions learned from heterogeneous datasets. Our algorithm relies on a mean field assumption for both the fused model and the individual dataset posteriors and proceeds using a simple assign-and-average approach. The components of the dataset posteriors are assigned to the proposed global model components by solving a regularized variant of the assignment problem. The global components are then updated based on these assignments by their mean under a KL divergence. For exponential family variational distributions, our formulation leads to an efficient non-parametric algorithm for computing the fused model. Our algorithm is easy to describe and implement, efficient, and competitive with state-of-the-art on motion capture analysis, topic modeling, and federated learning of Bayesian neural networks.

* ICML 2020 

  Access Paper or Ask Questions

Anomalous Sound Detection using unsupervised and semi-supervised autoencoders and gammatone audio representation

Jun 27, 2020
Sergi Perez-Castanos, Javier Naranjo-Alcazar, Pedro Zuccarello, Maximo Cobos

Anomalous sound detection (ASD) is, nowadays, one of the topical subjects in machine listening discipline. Unsupervised detection is attracting a lot of interest due to its immediate applicability in many fields. For example, related to industrial processes, the early detection of malfunctions or damage in machines can mean great savings and an improvement in the efficiency of industrial processes. This problem can be solved with an unsupervised ASD solution since industrial machines will not be damaged simply by having this audio data in the training stage. This paper proposes a novel framework based on convolutional autoencoders (both unsupervised and semi-supervised) and a Gammatone-based representation of the audio. The results obtained by these architectures substantially exceed the results presented as a baseline.

* Submitted to DCASE2020 Workshop, Workshop on Detection and Classification of Acoustic Scenes and Events 

  Access Paper or Ask Questions

Stopwords in Technical Language Processing

Jun 04, 2020
Serhad Sarica, Jianxi Luo

There are increasingly applications of natural language processing techniques for information retrieval, indexing and topic modelling in the engineering contexts. A standard component of such tasks is the removal of stopwords, which are uninformative components of the data. While researchers use readily available stopword lists which are derived for general English language, the technical jargon of engineering fields contains their own highly frequent and uninformative words and there exists no standard stopword list for technical language processing applications. Here we address this gap by rigorously identifying generic, insignificant, uninformative stopwords in engineering texts beyond the stopwords in general texts, based on the synthesis of alternative data-driven approaches, and curating a stopword list ready for technical language processing applications.


  Access Paper or Ask Questions

Finite Difference Neural Networks: Fast Prediction of Partial Differential Equations

Jun 02, 2020
Zheng Shi, Nur Sila Gulgec, Albert S. Berahas, Shamim N. Pakzad, Martin Takáč

Discovering the underlying behavior of complex systems is an important topic in many science and engineering disciplines. In this paper, we propose a novel neural network framework, finite difference neural networks (FDNet), to learn partial differential equations from data. Specifically, our proposed finite difference inspired network is designed to learn the underlying governing partial differential equations from trajectory data, and to iteratively estimate the future dynamical behavior using only a few trainable parameters. We illustrate the performance (predictive power) of our framework on the heat equation, with and without noise and/or forcing, and compare our results to the Forward Euler method. Moreover, we show the advantages of using a Hessian-Free Trust Region method to train the network.

* 38 pages, 48 figures 

  Access Paper or Ask Questions

Let Me Choose: From Verbal Context to Font Selection

May 03, 2020
Amirreza Shirani, Franck Dernoncourt, Jose Echevarria, Paul Asente, Nedim Lipka, Thamar Solorio

In this paper, we aim to learn associations between visual attributes of fonts and the verbal context of the texts they are typically applied to. Compared to related work leveraging the surrounding visual context, we choose to focus only on the input text as this can enable new applications for which the text is the only visual element in the document. We introduce a new dataset, containing examples of different topics in social media posts and ads, labeled through crowd-sourcing. Due to the subjective nature of the task, multiple fonts might be perceived as acceptable for an input text, which makes this problem challenging. To this end, we investigate different end-to-end models to learn label distributions on crowd-sourced data and capture inter-subjectivity across all annotations.

* Accepted to ACL 2020 

  Access Paper or Ask Questions

<<
227
228
229
230
231
232
233
234
235
236
237
238
239
>>