Physics-informed WNO learns PDE solutions without labeled data.
problem Data-hungry nature of WNO framework.
method Physics-informed WNO for learning PDE solutions.
result Validated and illustrated with four nonlinear systems.
Optical co-processor speeds up neural network training.
problem Expensive training costs for large neural networks.
method Direct feedback alignment, optical error projection.
result Optical co-processor trains neural networks for handwritten digit recognition.
Efficiently learns 3D convolutions with less data.
problem High parameter and data costs in 3D convolutions.
method Temporal factorization of 3D kernels.
result Significantly reduces training data requirement and parameter count.
Automatic summarisation is a popular approach to reduce a document to its main arguments. Recent research in the area has focused on neural approaches to summarisation, which can be very data-hungry. However, few large datasets exist and none for the traditionally popular domain of scientific publications, which opens …
Novel framework proves fast RL convergence in continuous spaces.
problem Analyzing stability in continuous state-action RL.
method Introduces a novel framework to analyze stability properties of RL.
result Highlights two key stability properties and demonstrates their satisfaction in RL.
In recent years, supervised machine learning models have demonstrated tremendous success in a variety of application domains. Despite the promising results, these successful models are data hungry and their performance relies heavily on the size of training data. However, in many healthcare applications it is difficult…
Deep neural networks are data hungry models and thus face difficulties when attempting to train on small text datasets. Transfer learning is a potential solution but their effectiveness in the text domain is not as explored as in areas such as image analysis. In this paper, we study the problem of transfer learning for…
Transformer learns long-term dependencies from real-world data.
problem Sample inefficiency in deep reinforcement learning.
method Transformer architecture applied to autoregressive real-world episodes.
result Transformer-based world model generates meaningful experience.
GANs can bias synthetic data, affecting minority and female faces.
problem GANs can amplify biases in synthetic data augmentation.
method Examine GANs on face-shots with gender and skin tone biases.
result GANs generate biased synthetic data, skewing minority modes and features.
SQS uses quantum kernels to improve credit scoring with fewer data points.
problem Credit scoring models struggle with scarce and skewed data.
method Systemic Quantum Score (SQS) leverages quantum kernels for better pattern extraction.
result SQS shows improved performance and pattern extraction with fewer data points.
The need for labour intensive pixel-wise annotation is a major limitation of many fully supervised learning methods for segmenting bioimages that can contain numerous object instances with thin separations. In this paper, we introduce a deep convolutional neural network for microscopy image segmentation. Annotation iss…
While deep learning has achieved remarkable results on various applications, it is usually data hungry and struggles to learn over non-stationary data stream. To solve these two limits, the deep learning model should not only be able to learn from a few of data, but also incrementally learn new concepts from data strea…
Proposes a synthesis algorithm using Conformal Prediction for improved Deep Learning performance.
problem Assessing the quality of synthesised data for high-stake domains.
method Conformal Prediction framework for generating data from high-confidence feature space regions.
result Training sets extended with confident synthesised data improved Deep Learning performance by up to 61 percentage points F1-score.
MDNs offer a data-efficient alternative to diffusion and flow models for multimodal scientific learning.
problem Capturing multimodal conditional uncertainty in scientific inverse problems.
method Mixture Density Networks (MDNs) as explicit parametric density estimators.
result MDNs achieve superior generalization, interpretability, and sample efficiency in scientific tasks.
In modern computer science education, massive open online courses (MOOCs) log thousands of hours of data about how students solve coding challenges. Being so rich in data, these platforms have garnered the interest of the machine learning community, with many new algorithms attempting to autonomously provide feedback t…
A new ML method speeds up PDE simulations without needing classical training.
problem Accelerating transient PDE simulations using machine learning.
method Online-learned preconditioners using a bandit algorithm.
result One-shot acceleration of PDE simulations.
Paper proposes a self-training method to generate molecular targets.
problem Challenges in training generative models for complex molecular design.
method Iterative target augmentation using a property predictor and EM iterations.
result Significant gains in molecular design, outperforming previous methods.
In recent years, deep learning models have shown great potential in source code modeling and analysis. Generally, deep learning-based approaches are problem-specific and data-hungry. A challenging issue of these approaches is that they require training from starch for a different related problem. In this work, we propo…
PropEn uses matching to create a larger dataset for efficient design optimization.
problem Limited data and complex landscapes in scientific applications.
method PropEn uses a matching approach to implicitly guide design without a discriminator.
result PropEn efficiently approximates the gradient of property improvement within the data distribution.
Study proposes a new method for deep portfolio optimization using residual factors.
problem Non-stationary financial market makes traditional machine learning methods ineffective.
method Predict distribution of residual factors using a novel neural network architecture with financial inductive biases.
result Demonstrated improved performance on U.S. and Japanese stock market data.
Hybrid QC system for Bengali questions using smart data balancing.
problem Classifying factoid questions in Bengali.
method Two-stage approach with 1D CNN for coarse classification and SGD for fine classification.
result Effectiveness of smart data balancing technique in improving classification accuracy.
Study reduces memory needs for active learning with enriched queries.
problem Expensive labeling costs in active learning.
method Introduces bounded memory active learning through enriched queries, introduces lossless sample compression.
result Can learn classifiers with bounded memory and query optimality.
New method improves Bayesian model selection for neural dynamics.
problem Bayesian methods struggle with large datasets and computational constraints.
method Computation-Aware State-Space Model (CASSM) with model selection.
result CASSM yields competitive performance and improved uncertainty calibration.
Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry and pose the challenges of not having adequate computing resources and of high costs involved in human labeling efforts. Training data subset selection and active learning techniques have been proposed as possible s…
BSA-TNP improves NP scalability and accuracy for spatiotemporal data.
problem Scalability and accuracy trade-off in Neural Processes.
method Introduces KRBlocks, group-invariant attention biases, and BSA for scalable spatiotemporal inference.
result BSA-TNP matches or exceeds accuracy of best models while training faster.
Generative AI models improve clinical trial data by generating survival outcomes.
problem Generating valid survival outcomes for clinical trials with synthetic data.
method A variational autoencoder (VAE) that jointly generates mixed-type covariates and survival outcomes.
result The method outperforms GAN baselines on fidelity, utility, and privacy metrics.
Develops a Bayesian framework for symbolic regression of scientific expressions.
problem Lack of principled uncertainty quantification and interpretability in existing symbolic regression methods.
method Hierarchical Bayesian framework with tree-structured symbolic expressions and Markov chain Monte Carlo inference.
result Robust performance on various datasets, including single-atom catalysis.
New analysis shows transfer learning can significantly reduce sample size for complex models.
problem Reducing sample size needed for complex models like large language models.
method Optimal transport viewpoint applied to analyze transfer learning efficiency.
result Transfer learning can achieve better sample efficiency for complex models.
Propagates adversarial robustness in federated learning.
problem Heterogeneous federated users with non-iid data and limited resources.
method Adversarial robustness propagation through batch-normalization.
result Federated models achieve remarkable robustness even with limited adversarial training.
SWIFT learns intrinsic rewards from LLM hidden states for efficient best-of-N sampling.
problem Efficiency and scalability of reward models for LLMs.
method SWIFT (Simple Weighted Intrinsic Feedback Technique) learns a reward function directly from LLM hidden states.
result SWIFT outperforms existing baselines by 12.7% on MATH dataset while using less than 0.005% of their parameters.
This paper explores emerging methods for estimating variable importance in machine learning.
problem Estimating the importance of variables in machine learning models.
method Least Absolute Shrinkage and Selection Operator (LASSO), Support Vector Machine (SVM), Predictive Error Function (PERF), Random Forest (RF), Extreme Gradient Boosting (XGBOOST).
result PERF and RF showed the best performance in highly correlated data, while PERF and XGBOOST performed poorly on small data sizes.
Recently, self-supervised learning has proved to be effective to learn representations of events suitable for temporal segmentation in image sequences, where events are understood as sets of temporally adjacent images that are semantically perceived as a whole. However, although this approach does not require expensive…
This paper proposes an unsupervised learning method to solve heat equations on chips.
problem Critical need for solving heat transfer equations on chips for 5G and AI.
method Hybrid framework of Auto Encoder and Image Gradient for unsupervised learning.
result Framework can solve heat transfer problems with a single training process and predict unseen cases.
Unified framework for blending ML and mechanistic models in dynamical systems.
problem Learning dynamical systems from noisy, partially observed data.
method A unifying framework that combines mechanistic and machine learning approaches.
result Proves that hybrid models can learn memory-dependent model error.
Adaptive batch size schedules improve language model training efficiency and generalization.
problem Dilemma of choosing batch sizes in large-scale model training.
method General-purpose adaptive batch size schedules compatible with data and model parallelism.
result Adaptive batch size schedules outperform constant batch sizes and heuristic warmup schedules.
ECG-DelNet uses neural networks to accurately delineate ECGs, even with low-quality data.
problem Lack of model explainability and small databases limit deep learning applicability in ECG detection.
method Adapted U-Net architecture for 1D data, used PhysioNet's QT database, applied data augmentation and regularization techniques.
result Best configuration achieved high precision and recall for P, QRS, and T waves.