New deep architecture improves head motion prediction in 360° videos.
problem Predicting user head motion in 360-degree videos using past positions and video content.
method Re-examined existing deep-learning approaches, identified flaws, and designed a new TRACK architecture.
result TRACK achieves state-of-the-art performance, outperforming competitors by up to 20 percent.
GWHD dataset offers 4,700 high-res images of wheat heads.
problem Challenges in wheat head detection from high-resolution imagery.
method Large, diverse dataset with detailed metadata.
result Benchmark for wheat head detection methods.
SigMA uses signatures and attention to estimate parameters in fBm-driven SDEs.
problem Estimating parameters in SDEs driven by fBm is challenging due to non-Markovian and semimartingale issues.
method SigMA integrates path signatures with multi-head self-attention, using convolutional and MLP layers.
result SigMA outperforms other methods in accuracy, robustness, and model compactness.
Deep learning predicts VR head movements for better 360-degree videos.
problem Predicting head movements in 360-degree VR videos.
method Deep learning network using position data and video content for long-term prediction.
result 16.1% improvement in prediction accuracy compared to baseline.
Multi-headed ensembles boost model performance with faster training.
problem Limited computational resources hinder ensemble search performance.
method Extend NES to multi-headed ensembles, leveraging end-to-end training and one-shot NAS methods.
result Multi-headed ensemble search finds robust ensembles 3 times faster with comparable performance.
New method removes contrastive loss by adding a prediction head, revealing learning mechanisms.
problem Understanding why neural networks learn competitive representations despite trivial optima.
method Empirical and theoretical analysis of a trainable, identity-initialized prediction head.
result The trainable prediction head enables learning all features, preventing dimensional collapse.
New algorithm disentangles latent space in GANs using video sequences.
problem Learning disentangled latent spaces in GANs without supervision.
method Adversarial training with video sequences, modifying standard GAN algorithm.
result Disentangled latent space into content and motion attributes.
Multi-head attention outperforms single-head in in-context linear regression tasks.
problem Comparing performance of transformer with single-/multi-head attention in in-context learning.
method Theoretical analysis of performance of transformers with different attention mechanisms in linear regression tasks.
result Multi-head attention with a substantial embedding dimension outperforms single-head attention in in-context linear regression tasks.
Language models can predict numeric values as strings.
problem Regression tasks with numeric predictions.
method Causal sequence decoding models trained for next-token prediction.
result Decoder-based heads perform as well as standard heads in numeric regression tasks.
In this paper, we present a data science automation system called Prediction Factory. The system uses several key automation algorithms to enable data scientists to rapidly develop predictive models and share them with domain experts. To assess the system's impact, we implemented 3 different interfaces for creating pre…
Annealing Double-Head calibrates deep neural networks during training.
problem Overestimation or underestimation of predictive confidence in deep neural networks.
method An additional calibration head and Annealing technique to dynamically scale logits.
result State-of-the-art model calibration performance achieved without post-processing.
The paper introduces a method to decompose variance in twin networks for better treatment effect estimation.
problem Accurate treatment effect estimation requires reliable uncertainty measures to locate model failures.
method Layer-wise variance decomposition using Monte Carlo Dropout in twin networks.
result The encoder component dominates under distributional shift, providing a practical diagnostic for data collection.
Improved GRU model with multi-head cross-attention enhances stock prediction accuracy.
problem Inaccurate stock prediction due to complex market dynamics and data sparsity.
method Enhanced GRU with multi-head cross-attention for better historical information selection and latent market state learning.
result The proposed MCI-GRU model outperforms state-of-the-art techniques in multiple metrics.
A novel spatio-temporal graph neural network with a learnable Tweedie head improves vessel traffic flow prediction in sparse maritime data.
problem Accurate vessel traffic flow prediction in sparse maritime data.
method A model-agnostic learnable Tweedie head attached to ST-GNN backbones.
result The proposed head consistently improves RMSE across multiple ST-GNN backbones, especially on non-zero events.
Study on multi-head softmax attention dynamics for in-context learning.
problem Understanding and optimizing multi-head softmax attention models for multi-task linear regression.
method Gradient flow analysis and spectral mapping technique.
result Gradient flow converges to optimal multi-head softmax attention model, with task allocation emerging during training.
Proposes a new neural head for asymmetric representation learning.
problem Asymmetric representation learning in directed relations.
method Role-aware neural convex divergence head.
result Role-aware projections improve directional accuracy over plain ICNN-Bregman heads.
Transformers learn to use induction heads or shortcuts based on data diversity.
problem How data diversity influences the behavior of transformers.
method Gradient-based training of a single-layer transformer on a minimal task.
result Data diversity steers transformers toward induction heads or shortcuts.
CARL controls a quadruped to move naturally in complex environments.
problem Motion synthesis in dynamic environments with complex constraints.
method CARL uses GANs to adapt high-level controls to action distributions and deep reinforcement learning for dynamic recovery.
result CARL can be controlled with high-level directives and react naturally to dynamic environments.
Deep neural network predicts traffic flow on city maps.
problem Short-term traffic flow prediction on high-resolution city maps.
method UNet-based deep convolutional neural network with densely connected layers.
result Best performance on the Traffic4cast challenge 2019.
Improved vehicle motion prediction with uncertainty estimation.
problem Robust motion prediction for autonomous vehicles, especially under distributional shift.
method Presented an approach significantly improving the benchmark and taking 2nd place on the leaderboard.
result Significantly improved motion prediction and uncertainty measurement.
Neural network predicts vessel motions with high accuracy.
problem Real-time prediction of heave and surge motions for improved performance and safety.
method Developed an LSTM-based machine learning model trained on measured waves and motion data.
result The model predicts vessel motions up to 46.5 seconds into the future with an average accuracy of 90%.
ConCare personalizes healthcare predictions by capturing EMR features.
problem Predicting patient outcomes from EMR data with personalization.
method Captures personal characteristics and time-aware distribution in EMR data.
result Improves healthcare prediction accuracy through personalized health context.
Hydra distills ensemble models into a single model while preserving diversity and uncertainty.
problem Loss of ensemble diversity and uncertainty in distilled models.
method Single multi-headed neural network with shared body network.
result Hydra improves distillation performance and preserves ensemble diversity and uncertainty.
The paper accelerates LLM inference by adding early exit heads trained in a self-supervised manner.
problem Inference speed in large language models (LLMs) is slow and resource-intensive.
method Adding self-supervised early exit heads at intermediate transformer layers to stop computation early based on confidence thresholds.
result Entropy provides the most reliable confidence metric for stopping computation early.
This paper proposes a multi-head attention model for predicting RUL in IIoT environments.
problem Estimating RUL for complex industrial equipment using IIoT data.
method Multi-Head Attention Mechanism combined with LSTM for multi-dimensional time-series data.
result The proposed model outperforms state-of-the-art models on benchmark datasets.
New framework predicts diverse, contextually plausible 3D human motions.
problem Predicting multiple plausible future 3D poses given observed poses.
method Developed a new variational framework that conditions latent variable on past observation to encourage relevant information.
result Our approach generates motions of higher quality and preserves contextual information.
Develops a new neural spike train decoding framework using topological data.
problem Decoding neural spike trains from head direction and grid cells.
method Combines simplicial complex discovery with deep learning to capture higher-order connectivity.
result Demonstrates effectiveness on head direction and trajectory prediction datasets.
A hybrid ML method improves ship response predictions across different sea conditions.
problem Improving accuracy and generalizability of ML methods for ship response predictions.
method A hybrid machine learning method that corrects forces in a low-fidelity equation of motion.
result The hybrid method offers improved prediction accuracy and generalizability compared to benchmarks.
Wearable computing is one of the fastest growing technologies today. Smart watches are poised to take over at least of half the wearable devices market in the near future. Smart watch screen size, however, is a limiting factor for growth, as it restricts practical text input. On the other hand, wearable devices have so…
Modular method predicts motion in crowded scenes using learned environment models.
problem Predicting motion in dynamic, crowded environments.
method Modular model of spatial and dynamic aspects, unsupervised adaptation to new tasks.
result Comparable performance to state-of-the-art, transferable across tasks.
Paper compares stock price prediction models using Heston and Geometric Brownian Motion.
problem Predicting stock prices accurately.
method Developed Heston and Geometric Brownian Motion models using Ito's lemma and Euler-Maruyama methods.
result Models outperform statistical indicators in predicting stock prices.
Improved motion prediction for self-driving cars using trajectory sets and auxiliary losses.
problem Accurately predicting future vehicle motion for self-driving cars.
method Classification over trajectory sets with an auxiliary loss for off-road predictions and spatial-temporal relationships.
result Significant improvement in motion prediction performance on small datasets using map information.
The majority of contemporary object-tracking approaches do not model interactions between objects. This contrasts with the fact that objects' paths are not independent: a cyclist might abruptly deviate from a previously planned trajectory in order to avoid colliding with a car. Building upon HART, a neural class-agnost…
Parts of Texas, Oklahoma, and Kansas have experienced increased rates of seismicity in recent years, providing new datasets of earthquake recordings to develop ground motion prediction models for this particular region of the Central and Eastern North America (CENA). This paper outlines a framework for using Artificial…
New theory shows how multi-head attention reduces variance and decorrelates outputs.
problem Understanding and optimizing multi-head attention in neural networks.
method Developed a statistical theory linking multi-head attention to ensemble Nadaraya-Watson estimators.
result MHA variance reduction depends on head decorrelation, not just head count.
Geometric theory of projection heads in self-supervised learning.
problem Dimensional collapse and information invariance trade-off in projection heads.
method Geometric modeling of projection heads as Riemannian metrics, analyzing Hessian eigenvalues, and tracking optimization geometry.
result Smooth nonlinear heads induce negative curvature, preventing collapse; linear and ReLU heads cannot.
Improved language models with talking-heads attention.
problem Language model perplexity and quality issues.
method Added linear projections in multi-head attention.
result Better perplexities and quality in language tasks.
New approach improves multi-head attention by making heads less similar.
problem Multi-head attention can lead to similar features, reducing model expressiveness.
method Proposes a non-parametric approach using Bayesian techniques to make heads repel each other.
result Improves feature diversity, leading to better representations and performance.
Study improves vehicle motion prediction by incorporating traffic density.
problem Lack of contextual knowledge in predicting driving behavior.
method Categorize and define external conditions, evaluate motion prediction approach.
result Traffic density significantly improves motion prediction accuracy.
Paper introduces regularization for multi-head attention to spot keywords.
problem Redundancy in multi-head attention leads to lack of rich information.
method Regularization technique to enforce orthogonality between attention heads.
result Significant improvement in keyword spotting performance.
DMGNN predicts 3D human motions using adaptive multiscale graphs.
problem Predicting 3D skeleton-based human motions accurately.
method Dynamic multiscale graph neural networks (DMGNN) with adaptive multiscale graphs and MGCU.
result DMGNN outperforms state-of-the-art methods in short and long-term predictions.
Deep forecasting models show output heads significantly improve performance on fat-tailed financial returns.
problem Improving deep learning models for forecasting fat-tailed financial returns.
method Comparison of backbone architectures and output heads (point, Gaussian, Gaussian mixture) on S&P 500 monthly log-returns.
result Switching from point to Gaussian heads improves CRPS by about 1.3 percent, and from Gaussian to mixture adds another 2.4 percent.
End-to-end learnable network for safer self-driving with interpretable intermediate representations.
problem Safe motion planning for self-driving vehicles.
method Differentiable semantic occupancy representation for cost calculation in motion planning.
result Significantly outperforms state-of-the-art planners in imitating human behaviors and producing safer trajectories.
Proposes a hybrid deep learning network for better heart failure survival prediction.
problem Improving survival prediction in heart failure patients.
method Joint analysis of cardiac motion features and clinical risk factors using a hybrid deep learning network.
result Optimal integration of clinical risk factors into deep prediction networks.
Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed attention. The multiple heads learn diverse types of word relationships. However, with standard softmax attention, all attention heads are de…
One-layer transformers can't solve induction heads task efficiently.
problem Solving the induction heads task efficiently with one-layer transformers.
method Communication complexity argument showing exponential size requirement.
result No one-layer transformer can solve the induction heads task efficiently.
FineHand learns hand shapes for better ASL recognition.
problem Difficult ASL recognition due to fast, articulate gestures.
method Combines manual and deep learning for hand shape embeddings, uses RNN for sequential gestures.
result Improved video gesture recognition accuracy on GMU-ASL51 benchmark.
Improved trajectory prediction for team sports using sparse outputs.
problem Challenging to train deep learning models for player trajectory prediction.
method Sparse trajectory prediction and constant acceleration interpolation.
result Interpolation improves performance for all tested models.