Single fisheye camera controls vehicle steering with neural networks.
problem Lateral control for autonomous vehicles using multiple cameras.
method Used a single fisheye camera for data generation and augmentation.
result 99% autonomy on urban road in simulator-based evaluation.
Deep learning models control vehicle dynamics on a track.
problem Coupled longitudinal and lateral control of a vehicle.
method Trained two neural networks (MLP and CNN) to compute controls based on high-fidelity simulations.
result Deep learning models outperform conventional controllers on a challenging track.
Digital twins improve single-arm trials by providing robust treatment effect estimates.
problem Lack of control arms in single-arm trials limits their gold-standard evidence.
method Outcome-model-based synthetic controls using machine learning models trained on historical data.
result Digital twins offer more robust treatment effect estimates and principled corrections.
The paper examines how macroeconomic control tools lost effectiveness, leading to a 'dark ages' period.
problem Loss of effectiveness of control tools in macroeconomic stabilization policy.
method Historical analysis of macroeconomic stabilization policy from 1948 to 1993.
result The overstatement of the Lucas critique and Kydland and Prescott's time-inconsistency led to a period of ineffective stabilization policy.
This paper controls a boundary term in Huisken's formula for entropy.
problem Entropy of translators and its behavior under mean curvature flow.
method Geometrically natural control of the boundary term in Huisken's monotonicity formula.
result Entropy of compact translators is bounded by boundary entropy and maximal cone density.
Improved reinforcement method for optimal control problems.
problem Optimal control problems with limited computational cost.
method Reinforced least squares Monte Carlo method for stochastic control problems.
result Significant improvement in method's efficiency and accuracy.
Novel approach uses quasi-conformal geometry for OSA classification from cephalometry.
problem Classifying obstructive sleep apnea (OSA) based on craniofacial profiles.
method Quasi-conformal geometry for local deformation analysis of 15 landmark points in lateral cephalograms.
result Proposed model achieves 92.5% testing accuracy.
Suitable lateral connections between encoder and decoder are shown to allow higher layers of a denoising autoencoder (dAE) to focus on invariant representations. In regular autoencoders, detailed information needs to be carried through the highest layers but lateral connections from encoder to decoder relieve this pres…
New method controls false discoveries in online testing with deadlines.
problem Controlling false discoveries in online hypothesis testing with decision deadlines.
method Benjamini-Hochberg-type procedure over a moving window of hypotheses with adaptive threshold parameters.
result Controls false discovery rate at every stage and adaptively chosen stopping times.
Spectral normalization stabilizes GANs by controlling gradient explosion and vanishing.
problem Stability and sample quality issues in GAN training.
method Spectral normalization controls gradient explosion and vanishing, improving GAN training stability and sample quality.
result Bidirectional Scaled Spectral Normalization (BSSN) outperforms standard spectral normalization in sample quality and training stability.
This paper uses deep learning to estimate flow fields from OCT images for laser ablation control.
problem Automatic control of laser bone ablation using 4D OCT images.
method Semi-supervised convolutional neural network for 2.5D scene flow estimation.
result Scene flow estimation enables markerless tracking and automated laser ablation control.
Study improves deep learning chest X-ray models by incorporating lateral views.
problem Lack of lateral views in training datasets limits deep learning performance.
method Used PadChest dataset with multiple views to explore merging methods.
result Incorporating lateral views increases model performance for 32 labels.
New approach solves utility maximization problems using Delta family.
problem Utility maximization in stochastic control problems.
method Directly solving DP equation with Delta function representation.
result Explicit series representation of value function.
Paper uses machine learning and SIR models to predict COVID-19 cases.
problem Predicting the spread of COVID-19 cases for control measures.
method Machine learning and SIR models (deterministic and stochastic) with numerical approximations.
result Predictions help in finding concrete actions to control the pandemic.
Many problems in financial engineering involve the estimation of unknown conditional expectations across a time interval. Often Least Squares Monte Carlo techniques are used for the estimation. One method that can be combined with Least Squares Monte Carlo is the "Regress-Later" method. Unlike conventional methods wher…
Considering the driving habits which are learned from the naturalistic driving data in the path-tracking system can significantly improve the acceptance of intelligent vehicles. Therefore, the goal of this paper is to generate the prediction results of lateral commands with confidence regions according to the reference…
Adaptive lateral connections improve visual action recognition.
problem Feedforward neural models lack feedback and lateral connections like the primate visual cortex.
method Dynamic weights in recurrent lateral connections, iteratively reintroduced input.
result Significant performance gains in visual action recognition without pretraining.
SDQL uses modular deep Q networks to efficiently learn multi-stage optimal control tasks.
problem Training complex deep reinforcement learning models for multi-stage control tasks is inefficient and unstable.
method Stacked Deep Q Learning (SDQL) with modular Q networks and backward training.
result SDQL efficiently learns optimal control policies for multi-stage tasks with high-dimensional state and action spaces.
Agent uses message passing to optimize robot navigation, balancing exploration and exploitation.
problem Optimizing robot navigation in continuous-valued spaces with uncertainty.
method Autoregressive active inference agent using message passing on a factor graph.
result Agent modulates action based on predictive uncertainty, leading to better model of dynamics.
Deep RL algorithms can overfit to early experiences, leading to poor performance.
problem Overfitting to early interactions in deep reinforcement learning.
method Proposed a mechanism to periodically reset part of the agent to mitigate overfitting.
result Periodic resetting improves performance in both discrete and continuous action domains.
Robotics: Rolling robots on a moving platform can be controlled.
problem Controlling the motion of rolling robots atop a moving platform.
method Developed a mathematical model and demonstrated simulations.
result Platform acceleration can control robot's heading and motion.
We present and analyze several strategies for improving the performance of stochastic variance-reduced gradient (SVRG) methods. We first show that the convergence rate of these methods can be preserved under a decreasing sequence of errors in the control variate, and use this to derive variants of SVRG that use growing…
This work refines imitation learning to approximate optimal state-feedback policies for a quadcopter model.
problem Designing optimal control policies for complex systems like quadcopters.
method Supervised imitation learning using deep neural networks trained on optimal trajectories.
result Deep neural networks can approximate optimal state-feedback policies with high accuracy, even with two layers.
The MIMIC-CXR dataset is (to date) the largest released chest x-ray dataset consisting of 473,064 chest x-rays and 206,574 radiology reports collected from 63,478 patients. We present the results of training and evaluating a collection of deep convolutional neural networks on this dataset to recognize multiple common t…
SECRM-2D improves RL-based autonomous driving with safety guarantees.
problem Safety and efficiency trade-offs in RL-based autonomous driving.
method RL-based controller with safety constraints for efficient and comfortable driving.
result SECRM-2D avoids crashes and improves efficiency and comfort compared to baselines.
We show how a deep denoising autoencoder with lateral connections can be used as an auxiliary unsupervised learning task to support supervised learning. The proposed model is trained to minimize simultaneously the sum of supervised and unsupervised cost functions by back-propagation, avoiding the need for layer-wise pr…
This paper connects ODEs to deep learning for better understanding and optimization.
problem Improving neural network behavior and training efficiency.
method Viewing DNN as ODE discretization and training as optimal control problem.
result Advantages of continuous models in specific applications and optimization methods.
Improved driver identification accuracy using steering wheel data.
problem Accurately identifying drivers based on naturalistic driving behavior.
method Novel approach for window length parameter design, leveraging GRUs neural network.
result Increased driver identification accuracy from under 15% to over 65%.
GIFsentiment predicts stock market returns and investor sentiment from social media GIFs.
problem Understanding investor sentiment in the stock market.
method Constructing a sentiment index from social media GIFs and analyzing its correlation with market returns and volume.
result GIFsentiment positively predicts stock market returns and negatively predicts returns for up to four weeks.
Lagrange's map construction ideas influenced later mathematicians.
problem Improving geographical map construction methods.
method Analyzing the impact of Lagrange's memoir on subsequent mathematical works.
result Lagrange's ideas were influential in later mathematical developments, particularly in geography.
In this work we consider the Taylor expansion of the exponential map of a submanifold immersed in R^n up to order three, in order to introduce the concepts of lateral and frontal deviation. We compute the directions of extreme lateral and frontal deviation for surfaces in R^3. Also we compute, by using the Taylor expan…
Traditional statistical theory assumes that the analysis to be performed on a given data set is selected independently of the data themselves. This assumption breaks downs when data are re-used across analyses and the analysis to be performed at a given stage depends on the results of earlier stages. Such dependency ca…
Sparse representations improve reinforcement learning performance.
problem TD Learning struggles with large state spaces and simple control tasks.
method Learned sparse representations to reduce state space and support generalization.
result Sparse representations enhance reinforcement learning performance on challenging tasks.
HawkesLLM models text generation with temporal influence, improving semantic alignment under limited memory.
problem Path-dependent uncertainty in agentic text-simulation systems.
method HawkesLLM framework separates temporal influence modeling from text generation, using a multivariate Hawkes process and a language model.
result HawkesLLM improves late-stage semantic alignment under a compact prompt-memory budget.
This paper will be splited into two papers and submited later.
Modified BP attribution methods often ignore later layers' information, leading to misleading explanations.
problem Misleading explanations from modified BP methods ignoring later layers' information.
method Analysis of 9 modified BP methods including Deep Taylor Decomposition, LRP, Excitation BP, PatternAttribution, DeepLIFT, Deconv, RectGrad, Guided BP.
result Only DeepLIFT does not ignore later layers' information, providing a faithful explanation.
In 1996, Huisken-Yau proved that every three-dimensional Riemannian manifold can be uniquely foliated near infinity by stable closed surfaces of constant mean curvature (CMC) if it is asymptotically equal to the (spatial) Schwarzschild solution. Later, their decay assumptions were weakened by Metzger, Huang, Eichmair-M…
When humans learn a new concept, they might ignore examples that they cannot make sense of at first, and only later focus on such examples, when they are more useful for learning. We propose incorporating this idea of tunable sensitivity for hard examples in neural network learning, using a new generalization of the cr…
RocketStack integrates predictions from multiple base learners using a recursive stacking architecture up to ten levels.
problem Feature redundancy, complexity, and computational burden in deep stacking.
method Level-aware recursive stacking with pruning and compression techniques.
result Increasing accuracy with depth and outperforming standalone ensembles at later levels.
New neural network avoids forgetting old knowledge as new data comes in.
problem Catastrophic forgetting in lifelong learning systems.
method Sequential Neural Coding Network, biologically-plausible synapse adaptation, task-executive control mimicry.
result Significantly less forgetting compared to standard neural models in experiments.
Paper tackles zero-shot policy learning for agents in new environments.
problem Learning in one environment and generalizing to unseen environments without additional data.
method Decomposes sparse rewards into spatial-temporal regions and uses Model Predictive Control (MPC).
result Method achieves natural generalization to new environments, demonstrated on various tasks.
Simultaneous Latent Budget Trees for stratified classification
problem Classification with stratification factors
method Probabilistic machine learning framework
result Interpretation of latent components and conditional split rule
SnareNet adds repair layers to neural networks to ensure outputs meet physical constraints.
problem Unconstrained neural network predictions violate physical or safety requirements.
method SnareNet appends a differentiable repair layer that navigates constraints to produce feasible outputs.
result SnareNet consistently improves objective quality while satisfying constraints more reliably.
Sharp stability of Möbius group among sphere-valued maps proved in arbitrary dimensions.
problem Proving a sharp quantitative form of Liouville's theorem for sphere-valued maps.
method New arguments and an inequality from Sobolev inequality proof.
result Sharp stability estimate for weakly conformal maps of arbitrary dimensions.
A paper uses RL to design microfluidic flow shapes efficiently.
problem Designing complex flow shapes in microfluidics using inverse problems.
method Formulated as a Reinforcement Learning (RL) problem, trained a DoubleDQN agent.
result Success frequency reached 90% in 200,000 episodes, rewards converged.
Develops a neural network for precise vehicle trajectory prediction.
problem Improving situational awareness in vehicular networks for safety applications.
method Two-layer neural network predicting vehicle parameters and trajectory points.
result Significantly improved prediction accuracy compared to existing methods.
A new method tackles nonconvex optimization with penalties and proximal terms.
problem Nonconvex optimization problems with equality and inequality constraints.
method Inexact proximal augmented Lagrangian method (P-ALM) with adaptive penalty and proximal parameters.
result Effective convergence properties and numerical superiority over traditional methods.
New algorithm learns deterministic policies in continuous domains using sign of advantage function.
problem Learning deterministic policies in continuous domains.
method Proposes a new trust region algorithm, Penalized NFAC (PeNFAC), based on a theoretical explanation of the advantage function.
result PeNFAC algorithm surpasses state-of-the-art algorithms in learning deterministic policies in classic control problems.