arXiv research

Tab-TRM uses recursive model for insurance pricing on tabular data.

Tiny Eats GRU detects eating episodes on a microcontroller.

Tiny benchmarks reduce LLM evaluation costs by using fewer examples.

Finding Tiny Faces (by Hu and Ramanan) proposes a novel approach to find small objects in an image. Our contribution consists in deeply understanding the choices of the paper together with applying and extending a similar method to a real world subject which is the counting of people in a public demonstration.

Tiny complexes share 3-5 triangles in common coverings.

ThriftyNet uses a single convolutional layer recursively to maximize parameter usage.

With the emergence of onboard vision processing for areas such as the internet of things (IoT), edge computing and autonomous robots, there is increasing demand for computationally efficient convolutional neural network (CNN) models to perform real-time object detection on resource constraints hardware devices. Tiny-YO…

A new clustering algorithm considers data smoothness for better performance.

EAST compresses deep ConvNets for tiny memory nodes.

New algorithm PRACTISE accelerates networks with tiny sets, reducing latency by 22%.

Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.

This work analyzes how frequency components affect CNN predictions and robustness.

Study Lie algebras with complex structures, focusing on degenerations and deformations.

POET enables large neural network training on tiny devices with reduced energy.

Flat space for manifolds with tiny curvature.

Softmax is found ineffective for NL block, leading to improved performance.

AL$\ell_0$CORE tensor decomposition reduces computational cost for sparse count data.

Improved robustness of machine learning models with controlled Lipschitz constants.

This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN limitations of inaccurate training and inefficient prediction. Previous approaches have improved accuracy at the expense of prediction costs making them infeasible for resource-constrained and real-time applications. Unitary RNNs have incre…

Puzzle Mix optimizes mixup by leveraging saliency and local statistics.

Over the past decade, deep neural networks (DNNs) have demonstrated remarkable performance in a variety of applications. As we try to solve more advanced problems, increasing demands for computing and power resources has become inevitable. Spiking neural networks (SNNs) have attracted widespread interest as the third-g…

Review of efficient neural networks for TinyML on resource-constrained devices.

We show that in a variety of large-scale deep learning scenarios the gradient dynamically converges to a very small subspace after a short period of training. The subspace is spanned by a few top eigenvectors of the Hessian (equal to the number of classes in the dataset), and is mostly preserved over long periods of tr…

A new mutual information optimization method using self-supervised binary contrastive learning.

Improved bound for optimal Moebius band aspect ratio.

Recent research showed that deep neural networks are highly sensitive to so-called adversarial perturbations, which are tiny perturbations of the input data purposely designed to fool a machine learning classifier. Most classification models, including deep learning models, are highly vulnerable to adversarial attacks.…

In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amount of supervision in the existing learning algorithms. But for a successful knowledge transfer, the learner needs to remember how to perform …

Paper trains a Transformer to add numbers of any length.

New framework explains adversarial examples in neural nets.

This paper represents a preliminary (pre-reviewing) version of a sublinear variational algorithm for isotropic Gaussian mixture models (GMMs). Further developments of the algorithm for GMMs with diagonal covariance matrices (instead of isotropic clusters) and their corresponding benchmarking results have been published…

GraphXCOVID uses deep semi-supervised learning to identify COVID-19 from chest X-rays with minimal labels.

A new learning scheme improves model efficiency and performance.

RobNets improve robustness of deep neural networks against adversarial attacks.

RoBERTa outperforms other pre-trained models in NER tasks.

A new approach of solving the ill-conditioned inverse problem for analytical continuation is proposed. The root of the problem lies in the fact that even tiny noise of imaginary-time input data has a serious impact on the inferred real-frequency spectra. By means of a modern regularization technique, we eliminate redun…

Proposes a method to improve neural architectures reproducibly.

Sharp results link DLN gradient flow to basis pursuit optimization and GHA phase transitions.

The paper examines stable CMC hypersurfaces with boundaries on parallel hyperplanes.

Efficiently estimates Gaussian distributions privately and robustly.

Large size models are implemented in recently ASR system to deal with complex speech recognition problems. The num- ber of parameters in these models makes them hard to deploy, especially on some resource-short devices such as car tablet. Besides this, at most of time, ASR system is used to deal with real-time problem …

Dropout is often used in deep neural networks to prevent over-fitting. Conventionally, dropout training invokes \textit{random drop} of nodes from the hidden layers of a Neural Network. It is our hypothesis that a guided selection of nodes for intelligent dropout can lead to better generalization as compared to the tra…

Current state-of-the-art nonparametric Bayesian text clustering methods model documents through multinomial distribution on bags of words. Although these methods can effectively utilize the word burstiness representation of documents and achieve decent performance, they do not explore the sequential information of text…

VoiceFilter-Lite separates speech from background in real-time for on-device speech recognition.

In this short article we investigate the topology of the moduli space of two-convex embedded tori $S^{n-1}\times S^1\subset \mathbb{R}^{n+1}$. We prove that for $n \geq 3$ this moduli space is path-connected, and that for $n = 2$ the connected components of the moduli space are in bijective correspondence with the knot…

Ball trajectory data are one of the most fundamental and useful information in the evaluation of players' performance and analysis of game strategies. Although vision-based object tracking techniques have been developed to analyze sport competition videos, it is still challenging to recognize and position a high-speed …

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…

Linear models can be poisoned by shifting a fraction of one class's data, revealing scaling laws and weight alignment.

Develops a method for manifold learning with small sample size datasets.