A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Improved student networks boost image accuracy by 10% with same inference time.
Binary neural networks trained from scratch achieve state-of-the-art results.
Nontrivial connectivity has allowed the training of very deep networks by addressing the problem of vanishing gradients and offering a more efficient method of reusing parameters. In this paper we make a comparison between residual networks, densely-connected networks and highway networks on an image classification tas…
DenseNets improve accuracy and efficiency in convolutional networks.
Detects anomalous behavior in social media users by analyzing content and connections.
Improves audio source separation using dilated convolutions and dense connections.
Finding "densely connected clusters" in a graph is in general an important and well studied problem in the literature \cite{Schaeffer}. It has various applications in pattern recognition, social networking and data mining \cite{Duda,Mishra}. Recently, Ames and Vavasis have suggested a novel method for finding cliques i…
A new deep learning method for tissue-cleared image registration.
Deep neural network predicts traffic flow on city maps.
New neural network architectures use signed permutation representations for finite groups, improving performance.
Capsule Networks improve clothing retrieval without landmark info.
Novel graph theory for neural networks improves understanding of their structure and performance.
Dense neural networks can't approximate all functions.
Networks, which represent agents and interactions between them, arise in myriad applications throughout the sciences, engineering, and even the humanities. To understand large-scale structure in a network, a common task is to cluster a network's nodes into sets called "communities", such that there are dense connection…
Method integrates functional data into neural networks for better interpretability.
New method selects neural network architectures without needing data.
The morphological structure of left ventricle segmented from cardiac magnetic resonance images can be used to calculate key clinical parameters, and it is of great significance to the accurate and efficient diagnosis of cardiovascular diseases. Compared with traditional methods, the segmentation algorithms based on ful…
In this work we introduce a time- and memory-efficient method for structured prediction that couples neuron decisions across both space at time. We show that we are able to perform exact and efficient inference on a densely connected spatio-temporal graph by capitalizing on recent advances on deep Gaussian Conditional …
A new neural network separates vocals from music accompaniment.
A new algorithm speeds up neural network derivative calculations.
FineMorphs models smooth transformations for multivariate regression.
Sparse routing networks with co-training prevent catastrophic forgetting in continual learning.
GHNet improves graph learning by balancing homogeneity and heterogeneity.
Achieving international food security requires improved understanding of how international trade networks connect countries around the world through the import-export flows of food commodities. The properties of food trade networks are still poorly documented, especially from a multi-network perspective. In particular,…
DVNet efficiently segments large neurovascular datasets using skip connections.
CAggNet improves medical image segmentation by fusing coarse and fine features.
In this work, we investigate the value of employing deep learning for the task of wireless signal modulation recognition. Recently in [1], a framework has been introduced by generating a dataset using GNU radio that mimics the imperfections in a real wireless channel, and uses 10 different modulation types. Further, a …
Economies grow by upgrading the type of products they produce and export. The technology, capital, institutions and skills needed to make such new products are more easily adapted from some products than others. We study the network of relatedness between products, or product space, finding that most upscale products a…
Networks are a convenient way to represent complex systems of interacting entities. Many networks contain "communities" of nodes that are more densely connected to each other than to nodes in the rest of the network. In this paper, we investigate the detection of communities in temporal networks represented as multilay…
We present a new notion of probabilistic duality for random variables involving mixture distributions. Using this notion, we show how to implement a highly-parallelizable Gibbs sampler for weakly coupled discrete pairwise graphical models with strictly positive factors that requires almost no preprocessing and is easy …
RDL-Net improves speech enhancement with fewer parameters and better performance.
The state of the art lung nodule detection studies rely on computationally expensive multi-stage frameworks to detect nodules from CT scans. To address this computational challenge and provide better performance, in this paper we propose S4ND, a new deep learning based method for lung nodule detection. Our approach use…
This paper proposes a new randomized strategy for adaptive MCMC using Bayesian optimization. This approach applies to non-differentiable objective functions and trades off exploration and exploitation to reduce the number of potentially costly objective function evaluations. We demonstrate the strategy in the complex s…
SWNets optimize DL architectures for faster convergence.
The paper uses neural networks to segment brain tumors and predict patient survival.
This paper introduces a hierarchical associative memory model with multiple layers.
Real-world networks usually have community structure, that is, nodes are grouped into densely connected communities. Community detection is one of the most popular and best-studied research topics in network science and has attracted attention in many different fields, including computer science, statistics, social sci…
Efficiently processes dynamic inputs in AI writing assistants with incremental computation.
Graph energy helps detect communities in networks better than traditional methods.
Deep neural network architectures have traditionally been designed and explored with human expertise in a long-lasting trial-and-error process. This process requires huge amount of time, expertise, and resources. To address this tedious problem, we propose a novel algorithm to optimally find hyperparameters of a deep n…
RobNets improve robustness of deep neural networks against adversarial attacks.
Chaos in cerebellar cells enhances complexity of neural patterns.
New models explain residual and dilated dense neural networks using sparse coding.
Study reveals how illiquidity network signals Chinese stock market crashes.
This paper proposes a principled information theoretic analysis of classification for deep neural network structures, e.g. convolutional neural networks (CNN). The output of convolutional filters is modeled as a random variable Y conditioned on the object class C and network filter bank F. The conditional entropy (CENT…
Graph kernel uses Ricci curvature for comparison.
The development of new technology such as wearables that record high-quality single channel ECG, provides an opportunity for ECG screening in a larger population, especially for atrial fibrillation screening. The main goal of this study is to develop an automatic classification algorithm for normal sinus rhythm (NSR), …
Partitioning a graph into groups of vertices such that those within each group are more densely connected than vertices assigned to different groups, known as graph clustering, is often used to gain insight into the organisation of large scale networks and for visualisation purposes. Whereas a large number of dedicated…