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.
Large receptive field CNNs improve distant speech recognition.
Optimizes CNN architectures by analyzing receptive fields without training.
Convolutional Neural Networks (CNN) and the locally connected layer are limited in capturing the importance and relations of different local receptive fields, which are often crucial for tasks such as face verification, visual question answering, and word sequence prediction. To tackle the issue, we propose a novel loc…
Acoustic scene classification and related tasks have been dominated by Convolutional Neural Networks (CNNs). Top-performing CNNs use mainly audio spectograms as input and borrow their architectural design primarily from computer vision. A recent study has shown that restricting the receptive field (RF) of CNNs in appro…
Convolutional Neural Networks (CNNs) have had great success in many machine vision as well as machine audition tasks. Many image recognition network architectures have consequently been adapted for audio processing tasks. However, despite some successes, the performance of many of these did not translate from the image…
A simple block configures optimal kernel sizes for time series classification.
Enhanced image denoising with MWRDCNN using residual dense blocks.
PatchGuard defends against localized adversarial patches with provable robustness.
ARMA nets expand receptive fields for dense prediction tasks.
We establish large deviation principles for convolutional neural networks.
Deep CNN predicts disruptions in fusion plasmas with high accuracy.
We propose a new model for unsupervised document embedding. Leading existing approaches either require complex inference or use recurrent neural networks (RNN) that are difficult to parallelize. We take a different route and develop a convolutional neural network (CNN) embedding model. Our CNN architecture is fully par…
Neuroscientists classify neurons into different types that perform similar computations at different locations in the visual field. Traditional methods for neural system identification do not capitalize on this separation of 'what' and 'where'. Learning deep convolutional feature spaces that are shared among many neuro…
A new framework for flexible neural network receptive fields.
Deep convolutional neural networks (CNNs) have demonstrated impressive performance on visual object classification tasks. In addition, it is a useful model for predication of neuronal responses recorded in visual system. However, there is still no clear understanding of what CNNs learn in terms of visual neuronal circu…
Modern deep neural networks require a tremendous amount of data to train, often needing hundreds or thousands of labeled examples to learn an effective representation. For these networks to work with less data, more structure must be built into their architectures or learned from previous experience. The learned weight…
Graph convolutional networks (GCNs) are powerful deep neural networks for graph-structured data. However, GCN computes the representation of a node recursively from its neighbors, making the receptive field size grow exponentially with the number of layers. Previous attempts on reducing the receptive field size by subs…
Combines CNN and Transformer for financial time series forecasting.
The challenge of object categorization in images is largely due to arbitrary translations and scales of the foreground objects. To attack this difficulty, we propose a new approach called collaborative receptive field learning to extract specific receptive fields (RF's) or regions from multiple images, and the selected…
Post-hoc explanations improve CNNs by replacing final linear layer with k-means classifier.
New approach to deeper graph neural networks to avoid performance degradation.
Group-equivariant subsampling layers improve CNNs' equivariance.
In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size. Such operation is commonly so-called pooling. Maximation and averaging over sliding windows (max/average pooling), and plain downsampling in the form of strided convoluti…
Expanding the receptive field to capture large-scale context is key to obtaining good performance in dense prediction tasks, such as human pose estimation. While many state-of-the-art fully-convolutional architectures enlarge the receptive field by reducing resolution using strided convolution or pooling layers, the mo…
This study presents a novel, deep, fully convolutional architecture which is optimized for the task of EEG-based neonatal seizure detection. Architectures of different depths were designed and tested; varying network depth impacts convolutional receptive fields and the corresponding learned feature complexity. Two deep…
Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map translations. This is not the case for rotations. Global rotation equivariance is typic…
Convolutional neural networks (CNNs) have achieved great success on grid-like data such as images, but face tremendous challenges in learning from more generic data such as graphs. In CNNs, the trainable local filters enable the automatic extraction of high-level features. The computation with filters requires a fixed …
Seq-U-Net improves sequence modeling efficiency with dilated U-Net.
New mechanisms from primate vision improve neural network robustness.
Convolutional neural networks (CNNs) can be applied to graph similarity matching, in which case they are called graph CNNs. Graph CNNs are attracting increasing attention due to their effectiveness and efficiency. However, the existing convolution approaches focus only on regular data forms and require the transfer of …
This paper solves deep learning's edge sensitivity issue by swapping important and irrelevant segments in synthetic data.
Advocates against over-smoothing and over-squashing in GNNs, suggesting they are less critical than previously thought.
DeepMap learns deep graph representations via CNNs, improving graph classification performance.
Deep Convolutional Neural Networks (DCNNs) are used extensively in medical image segmentation and hence 3D navigation for robot-assisted Minimally Invasive Surgeries (MISs). However, current DCNNs usually use down sampling layers for increasing the receptive field and gaining abstract semantic information. These down s…
New method shows fully-connected networks can learn convolutional structures from data.
This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The model provides adaptive and differentiable local connectivity (plasticity) applicable to any domain. It requires no other tool than the backpropagation algorithm to learn its parameters whi…
HGNet improves GNNs' ability to handle long-range interactions in graphs.
Modern audio source separation techniques rely on optimizing sequence model architectures such as, 1D-CNNs, on mixture recordings to generalize well to unseen mixtures. Specifically, recent focus is on time-domain based architectures such as Wave-U-Net which exploit temporal context by extracting multi-scale features. …
Two graph auto-encoders decouple feature propagation from graph convolution layers.
Proposes SimPool for graph pooling using structural similarity features.
To alleviate sparsity and cold start problem of collaborative filtering based recommender systems, researchers and engineers usually collect attributes of users and items, and design delicate algorithms to exploit these additional information. In general, the attributes are not isolated but connected with each other, w…
DRFormer uses dynamic tokenization and multi-scale transformer to forecast long time series.
gLSTM improves graph neural networks by increasing storage capacity to prevent over-squashing.
Spiking neural networks perform similarly to deep networks on occluded images.
Quantitative susceptibility mapping (QSM) is a powerful MRI technique that has shown great potential in quantifying tissue susceptibility in numerous neurological disorders. However, the intrinsic ill-posed dipole inversion problem greatly affects the accuracy of the susceptibility map. We propose QSMGAN: a 3D deep con…
Convolutional Neural Networks (CNNs) have been recently introduced in the domain of session-based next item recommendation. An ordered collection of past items the user has interacted with in a session (or sequence) are embedded into a 2-dimensional latent matrix, and treated as an image. The convolution and pooling op…
The paper develops models to understand sensory coding and cortical topography.
Learning representations that accurately capture long-range dependencies in sequential inputs -- including text, audio, and genomic data -- is a key problem in deep learning. Feed-forward convolutional models capture only feature interactions within finite receptive fields while recurrent architectures can be slow and …