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 image classification accuracy on CIFAR-10 dataset.
Adversarial examples are of wide concern due to their impact on the reliability of contemporary machine learning systems. Effective adversarial examples are mostly found via white-box attacks. However, in some cases they can be transferred across models, thus enabling them to attack black-box models. In this work we ev…
Improves interpretability of neural network intermediate layers by making concept activations more robust and effective.
This study compares two methods for uncertainty estimation in CNNs, finding Conformal Prediction more reliable.
Deep learning models are vulnerable to adversarial attacks, leading to critical errors.
DeepStreamCE detects new classes in streaming deep neural networks.
Deep CNNs diagnose chest X-rays for COVID-19 and other pneumonia.
Feature attribution methods, or saliency maps, are one of the most popular approaches for explaining the decisions of complex machine learning models such as deep neural networks. In this study, we propose a stochastic optimization approach for the perturbation-based feature attribution method. While the original optim…
While several feature scoring methods are proposed to explain the output of complex machine learning models, most of them lack formal mathematical definitions. In this study, we propose a novel definition of the feature score using the maximally invariant data perturbation, which is inspired from the idea of adversaria…
We study the training process of Deep Neural Networks (DNNs) from the Fourier analysis perspective. We demonstrate a very universal Frequency Principle (F-Principle) -- DNNs often fit target functions from low to high frequencies -- on high-dimensional benchmark datasets such as MNIST/CIFAR10 and deep neural networks s…
Foraminifera are single-celled marine organisms, which may have a planktic or benthic lifestyle. During their life cycle they construct shells consisting of one or more chambers, and these shells remain as fossils in marine sediments. Classifying and counting these fossils have become an important tool in e.g. oceanogr…
A human does not have to see all elephants to recognize an animal as an elephant. On contrast, current state-of-the-art deep learning approaches heavily depend on the variety of training samples and the capacity of the network. In practice, the size of network is always limited and it is impossible to access all the da…
Image classification system identifies bumble bee species from images.
Mobile electrocardiogram (ECG) recording technologies represent a promising tool to fight the ongoing epidemic of cardiovascular diseases, which are responsible for more deaths globally than any other cause. While the ability to monitor one's heart activity at any time in any place is a crucial advantage of such techno…
With the increase in the amount of data and the expansion of model scale, distributed parallel training becomes an important and successful technique to address the optimization challenges. Nevertheless, although distributed stochastic gradient descent (SGD) algorithms can achieve a linear iteration speedup, they are l…
CNNs help diagnose diabetic retinopathy by localizing lesions.
NullSpaceNet maps inputs to a joint-nullspace for clearer class separability.
Study identifies and mitigates causes of image misclassifications in CNN models.
As Machine Learning (ML) gets applied to security-critical or sensitive domains, there is a growing need for integrity and privacy for outsourced ML computations. A pragmatic solution comes from Trusted Execution Environments (TEEs), which use hardware and software protections to isolate sensitive computations from the…
Novel covariance function improves Bayesian optimization efficiency.
Our community has greatly improved the efficiency of deep learning applications, including by exploiting sparsity in inputs. Most of that work, though, is for inference, where weight sparsity is known statically, and/or for specialized hardware. We propose a scheme to leverage dynamic sparsity during training. In parti…
Neural networks learn patterns in random data, improving downstream performance.
A new pruning method reduces neural network computation without retraining.
A new framework compresses neural networks using sparse optimization.
Channel Pruning, widely used for accelerating Convolutional Neural Networks, is an NP-hard problem due to the inter-layer dependency of channel redundancy. Existing methods generally ignored the above dependency for computation simplicity. To solve the problem, under the Bayesian framework, we here propose a layer-wise…
A hybrid method improves Convolutional Neural Networks training.
Paper introduces a new adaptive gradient method with gradient compression for distributed training.
AriaNN enables private deep learning with minimal interaction and reduced key sizes.
Novel framework for whole-slide blood cell segmentation.
RS-NN predicts belief functions for classification, improving accuracy and uncertainty estimation.
Predicts trainability of deep neural networks using reconstruction entropy.
A new pruning method finds sparse minimizers in flat regions of deep neural networks.
Forecast dam inflow using sea surface feature weights.
This paper speeds up K-FAC for deep learning by focusing on only a few eigen-modes.
Simple technique turns any adversarial attack into a universal one using few test examples.
Introduces fuzzy layers to enhance deep learning performance.
We propose a new metaheuristic training scheme that combines Stochastic Gradient Descent (SGD) and Discrete Optimization in an unconventional way. Our idea is to define a discrete neighborhood of the current SGD point containing a number of "potentially good moves" that exploit gradient information, and to search this …
Intelligent Object manipulation for grasping is a challenging problem for robots. Unlike robots, humans almost immediately know how to manipulate objects for grasping due to learning over the years. A grown woman can grasp objects more skilfully than a child because of learning skills developed over years, the absence …
Given two or more Deep Neural Networks (DNNs) with the same or similar architectures, and trained on the same dataset, but trained with different solvers, parameters, hyper-parameters, regularization, etc., can we predict which DNN will have the best test accuracy, and can we do so without peeking at the test data? In …
We propose a random convolutional neural network to generate a feature space in which we study image classification and retrieval performance. Put briefly we apply random convolutional blocks followed by global average pooling to generate a new feature, and we repeat this k times to produce a k-dimensional feature spac…