相关论文: Hamming Similarity and Graph Laplacians for Class …

Previous work has shown that a neural network with the rectified linear unit (ReLU) activation function leads to a convex polyhedral decomposition of the input space. These decompositions can be represented by a dual graph with vertices…

Graph Laplacians as well as related spectral inequalities and (co-)homology provide a foray into discrete analogues of Riemannian manifolds, providing a rich interplay between combinatorics, geometry and theoretical physics. We apply some…

Neural networks are playing a crucial role in everyday life, with the most modern generative models able to achieve impressive results. Nonetheless, their functioning is still not very clear, and several strategies have been adopted to…

This paper explores the topological signatures of ReLU neural network activation patterns. We consider feedforward neural networks with ReLU activation functions and analyze the polytope decomposition of the feature space induced by the…

Feed-forward networks can be interpreted as mappings with linear decision surfaces at the level of the last layer. We investigate how the tangent space of the network can be exploited to refine the decision in case of ReLU (Rectified Linear…

In this paper I review the submission to the Explaining the Human Visual Brain Challenge 2019 in both the fMRI and MEG tracks. The goal was to construct neural network features which generate the so-called representational dissimilarity…

Classification of biological images is an important task with crucial application in many fields, such as cell phenotypes recognition, detection of cell organelles and histopathological classification, and it might help in early medical…

Deep neural networks paved the way for significant improvements in image visual categorization during the last years. However, even though the tasks are highly varying, differing in complexity and difficulty, existing solutions mostly build…

Adversarial algorithms have shown to be effective against neural networks for a variety of tasks. Some adversarial algorithms perturb all the pixels in the image minimally for the image classification task in image classification. In…

Recent Progress has shown that exploitation of hidden layer neurons in convolution neural networks incorporating with a carefully designed activation function can yield better classification results in the field of computer vision. The…

The task of image segmentation is to classify each pixel in the image based on the appropriate label. Various deep learning approaches have been proposed for image segmentation that offers high accuracy and deep architecture. However, the…

In the deep metric learning approach to image segmentation, a convolutional net densely generates feature vectors at the pixels of an image. Pairs of feature vectors are trained to be similar or different, depending on whether the…

As modern deep learning architectures grow in complexity, representational ambiguity emerges as a critical barrier to their interpretability and reliable merging. For ReLU networks, identical functional mappings can be achieved through…

How data is represented and operationalized is critical for building computational solutions that are both effective and efficient. A common approach is to represent data objects as binary vectors, denoted \textit{hash codes}, which require…

What representation do deep neural networks learn? How similar are images to each other for neural networks? Despite the overwhelming success of deep learning methods key questions about their internal workings still remain largely…

Deep learning has greatly improved visual recognition in recent years. However, recent research has shown that there exist many adversarial examples that can negatively impact the performance of such an architecture. This paper focuses on…

We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification. It is a simple residual network that alternates (i) a linear layer in which image patches interact, independently and identically…

The input space of a neural network with ReLU-like activations is partitioned into multiple linear regions, each corresponding to a specific activation pattern of the included ReLU-like activations. We demonstrate that this partition…

Neural network based classifiers are still prone to manipulation through adversarial perturbations. State of the art attacks can overcome most of the defense or detection mechanisms suggested so far, and adversaries have the upper hand in…

Neural networks are frequently used for image classification, but can be vulnerable to misclassification caused by adversarial images. Attempts to make neural network image classification more robust have included variations on…