arXiv research

Extends driving model to control agent behavior in simulations.

Extends hyperparameter transfer across model sizes and modules, improving training speed.

Photonic chip speeds up option pricing with GAN for financial efficiency.

The paper proposes a method for interpretable mixture density estimation using a tree structure.

Non-autoregressive method speeds up protein folding prediction 23 times.

3D HQFTs constructed using graded monoidal categories.

Hybrid model improves wind speed prediction accuracy using MLP and WOA.

Spectrum selectively trains LLMs based on SNR to save resources.

The paper studies how certain surfaces evolve in space without collapsing.

Training a Neural Network (NN) with lots of parameters or intricate architectures creates undesired phenomena that complicate the optimization process. To address this issue we propose a first modular approach to NN design, wherein the NN is decomposed into a control module and several functional modules, implementing …

Improved YOLOv5 model detects mask-wearing with enhanced accuracy.

Presents SPEED, an algorithm for optimal policy evaluation in linear bandits with heteroscedastic noise.

Adversaries can fool deep learning modulator classifiers over wireless channels.

New STDP rule for spiking neurons solves discrete action reinforcement learning tasks.

Paper accelerates nonlinear mapping in online systems with lower time complexity.

Insurance firms use RL to optimize customer offers for desired target portfolios.

Improves sampling speed of ARM models without losing accuracy.

New method speeds up diffusion models without requiring complex assumptions.

Proposes a new method to improve target annotation in ATR.

Worldsheet skein D-module for Hopf link conormal uniquely determines partition functions.

Accurately tracking and predicting behaviors of surrounding objects are key prerequisites for intelligent systems such as autonomous vehicles to achieve safe and high-quality decision making and motion planning. However, there still remain challenges for multi-target tracking due to object number fluctuation and occlus…

Kriformer uses graph transformers to estimate data in sparse sensor areas.

Improves AI agents' 3D navigation by learning from failures and 3D spatial relationships.

GenFormer uses deep learning to generate complex stochastic data.

A new update rule for deep reinforcement learning reduces learning variance and variance in reference signals.

Diffractive deep neural network (DNNet) is a novel machine learning framework on the modulation of optical transmission. Diffractive network would get predictions at the speed of light. It's pure passive architecture, no additional power consumption. We improved the accuracy of diffractive network with optical waves at…

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 …

Recently the author has introduced cobordism-like modules induced from generic maps whose codimensions are negative. They are generalizations of cobordism modules of manifolds. They have been introduced in generalizing the following theorem shown by Hiratuka and Saeki in 2013--14; for a generic map whose codimension is…

Lung cancer continues to be a major healthcare challenge with high morbidity and mortality rates among both men and women worldwide. The majority of lung cancer cases are of non-small cell lung cancer type. With the advent of targeted cancer therapy, it is imperative not only to properly diagnose but also sub-classify …

System detects financial forecasts in tweets, achieving high precision.

In this paper, we present a new approach to Transfer Learning (TL) in Reinforcement Learning (RL) for cross-domain tasks. Many of the available techniques approach the transfer architecture as a method of speeding up the target task learning. We propose to adapt and reuse the mapped source task optimal-policy directly …

A framework for using auxiliary data to improve few-shot learning.

New RL approach speeds up training across tasks.

Researchers use Gaussian Process Regression to improve accuracy of a low-cost hot-wire anemometer.

This paper presents a new Graph Neural Network (GNN) type using feature-wise linear modulation (FiLM). Many standard GNN variants propagate information along the edges of a graph by computing "messages" based only on the representation of the source of each edge. In GNN-FiLM, the representation of the target node of an…

Non-parallel voice conversion (VC) is a technique for learning the mapping from source to target speech without relying on parallel data. This is an important task, but it has been challenging due to the disadvantages of the training conditions. Recently, CycleGAN-VC has provided a breakthrough and performed comparably…

Determining what experience to generate to best facilitate learning (i.e. exploration) is one of the distinguishing features and open challenges in reinforcement learning. The advent of distributed agents that interact with parallel instances of the environment has enabled larger scales and greater flexibility, but has…

We consider branched coverings which are simple in the sense that any point of the target has at most one singular preimage. The cobordism classes of $k$-fold simple branched coverings between $n$-manifolds form an abelian group $Cob^1(n,k)$. Moreover, $Cob^1(*,k) = \bigoplus_{n=0}^{\infty} Cob^1(n,k)$ is a module over…

Graphical models help infer domain adaptation across unknown distributions.

NIPA aims to translate brain learning mechanisms into scalable Bayesian inference.

Time-aware deep learning methods improve spatial downscaling of atmospheric pollutants.

Neural waveform models such as WaveNet have demonstrated better performance than conventional vocoders for statistical parametric speech synthesis. As an autoregressive (AR) model, WaveNet is limited by a slow sequential waveform generation process. Some new models that use the inverse-autoregressive flow (IAF) can gen…

Recent studies have shown that neural models can achieve high performance on several sequence labelling/tagging problems without the explicit use of linguistic features such as part-of-speech (POS) tags. These models are trained only using the character-level and the word embedding vectors as inputs. Others have shown …

Integrating wind power into the grid is challenging because of its random nature. Integration is facilitated with accurate short-term forecasts of wind power. The paper presents a spatio-temporal wind speed forecasting algorithm that incorporates the time series data of a target station and data of surrounding stations…

Study of 2d gauged linear sigma models to derive difference equations and spectral data.

Paper accelerates diffusion models, improving sampling speed.

Enhances GNNs for causal relationship learning.

A fast algorithm speeds up training of pairwise kernels.