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.
Adds a precortical module to CNNs for improved robustness to light variations.
Paper presents a light-weight CNN model for Parkinson's disease diagnosis.
STC systems improved deep learning for ASVspoof2019 challenge.
Improves CNN robustness by reducing texture bias.
AT-CNNs show improved shape recognition over texture recognition.
iSTFTNet2 improves iSTFTNet's speed and lightness with 1D-2D CNN.
Numerous pattern recognition applications can be formed as learning from graph-structured data, including social network, protein-interaction network, the world wide web data, knowledge graph, etc. While convolutional neural network (CNN) facilitates great advances in gridded image/video understanding tasks, very limit…
Cosmologists are facing the problem of the analysis of a huge quantity of data when observing the sky. The methods used in cosmology are, for the most of them, relying on astrophysical models, and thus, for the classification, they usually use a machine learning approach in two-steps, which consists in, first, extracti…
Hash codes are efficient data representations for coping with the ever growing amounts of data. In this paper, we introduce a random forest semantic hashing scheme that embeds tiny convolutional neural networks (CNN) into shallow random forests, with near-optimal information-theoretic code aggregation among trees. We s…
The Zone of Avoidance makes it difficult for astronomers to catalogue galaxies at low latitudes to our galactic plane due to high star densities and extinction. However, having a complete sky map of galaxies is important in a number of fields of research in astronomy. There are many unclassified sources of light in the…
A new CNN-based algorithm improves Fourier ptychography for faster, more robust image reconstruction.
Mobile app uses CNN to help visually impaired cross streets.
In this paper, we investigate the design and implementation of machine learning (ML) based demodulation methods in the physical layer of visible light communication (VLC) systems. We build a flexible hardware prototype of an end-to-end VLC system, from which the received signals are collected as the real data. The data…
A simple block configures optimal kernel sizes for time series classification.
JD.com uses a new CNN model to improve ad click prediction.
Noise is an inherent issue of low-light image capture, one which is exacerbated on mobile devices due to their narrow apertures and small sensors. One strategy for mitigating noise in a low-light situation is to increase the shutter time of the camera, thus allowing each photosite to integrate more light and decrease n…
Given the ability to directly manipulate image pixels in the digital input space, an adversary can easily generate imperceptible perturbations to fool a Deep Neural Network (DNN) image classifier, as demonstrated in prior work. In this work, we propose ShapeShifter, an attack that tackles the more challenging problem o…
SimCLR pre-training improves CNN performance with fewer labels.
mm-Pose detects human skeletons in real-time using mmWave radar and CNNs.
Convolution as inner product has been the founding basis of convolutional neural networks (CNNs) and the key to end-to-end visual representation learning. Benefiting from deeper architectures, recent CNNs have demonstrated increasingly strong representation abilities. Despite such improvement, the increased depth and l…
A CNN-based method detects and counts corn kernels from images.
A new text classification method using separable convolution reduces memory consumption.
Our goal is to design architectures that retain the groundbreaking performance of CNNs for landmark localization and at the same time are lightweight, compact and suitable for applications with limited computational resources. To this end, we make the following contributions: (a) we are the first to study the effect of…
ALCNN predicts bike demand patterns in new cities using multi-source geographic data.
Paper proposes a method to detect glare in document images.
New approximative kernels improve PDE-G-CNNs for geometric deep learning.
In recent years, deep learning poses a deep technical revolution in almost every field and attracts great attentions from industry and academia. Especially, the convolutional neural network (CNN), one representative model of deep learning, achieves great successes in computer vision and natural language processing. How…
Convolutional Neural Networks (CNNs) have revolutionized performances in several machine learning tasks such as image classification, object tracking, and keyword spotting. However, given that they contain a large number of parameters, their direct applicability into low resource tasks is not straightforward. In this w…
Simplified Butterfly-Net2 improves CNN efficiency in solving PDEs and signal processing tasks.
2D CNNs approximate Korobov functions with near-optimal rates.
New IP analysis for deep neural networks using Rényi's entropy and tensor kernels.
New metrics differentiate effective OOD sets for training calibrated CNNs.
In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult categories demand more dedicated classifiers. However, existing deep convolutional neural networks (CNN) are trained as flat N-way classifi…
Proposes a fixed smooth convolutional layer to reduce checkerboard artifacts in CNNs.
In this paper, we address the issue of how to enhance the generalization performance of convolutional neural networks (CNN) in the early learning stage for image classification. This is motivated by real-time applications that require the generalization performance of CNN to be satisfactory within limited training time…
TinyCNN accelerates CNN models on embedded FPGA with 15x speedup.
DoPa detects various physical adversarial attacks on CNNs.
Study improves CNNs for audio scene classification by restricting receptive fields and adding frequency awareness.
Simple 1D-CNN network predicts electricity loads 36 hours ahead.
This paper proposes a framework based on deep convolutional neural networks (CNNs) for automatic heart sound classification using short-segments of individual heart beats. We design a 1D-CNN that directly learns features from raw heart-sound signals, and a 2D-CNN that takes inputs of two- dimensional time-frequency fea…
This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., the explainer uses interpretable visual concepts to explain features in middle conv-layers of a CNN. Given feature maps of a conv-layer of the CNN, the explaine…
State-of-the-art image recognition systems use sophisticated Convolutional Neural Networks (CNNs) that are designed and trained to identify numerous object classes. Such networks are fairly resource intensive to compute, prohibiting their deployment on resource-constrained embedded platforms. On one hand, the ability t…
Convolutional neural networks (CNN) have achieved state of the art performance on both classification and segmentation tasks. Applying CNNs to microscopy images is challenging due to the lack of datasets labeled at the single cell level. We extend the application of CNNs to microscopy image classification and segmentat…
Improved robustness of 1D CNNs for heart arrhythmia classification.
Efficient CNN for VQA achieves similar performance to standard models.
Using open source data, we observe the fascinating dynamics of nighttime light. Following a global economic regime shift, the planetary center of light can be seen moving eastwards at a pace of about 60 km per year. Introducing spatial light Gini coefficients, we find a universal pattern of human settlements across dif…
Computer vision performances have been significantly improved in recent years by Convolutional Neural Networks(CNN). Currently, applications using CNN algorithms are deployed mainly on general purpose hardwares, such as CPUs, GPUs or FPGAs. However, power consumption, speed, accuracy, memory footprint, and die size sho…
Deep learning and prior maps improve traffic light recognition for autonomous cars.