Defines interpretability in machine learning and introduces PDR framework.
problem Confusion about interpretability and lack of common evaluation criteria.
method PDR framework: predictive, descriptive, relevancy.
result Provides a common vocabulary for interpretation methods.
A new objective function for NMF reduces model complexity and improves accuracy.
problem NMF's error-based objective function can lead to overly complex models.
method MDL-NMF uses minimum description length to balance model complexity and accuracy.
result MDL-NMF outperforms traditional NMF on various datasets.
A novel method computes Wigner kernels for atomic environments, achieving state-of-the-art accuracy.
problem Efficiently describing local atomic environments in materials science.
method Computes fully equivariant and body-ordered kernels iteratively, independent of basis.
result Achieves state-of-the-art accuracy on the QM9 benchmark dataset.
DRAGON improves learning for rare classes in unbalanced datasets using class descriptions.
problem Learning rare classes in unbalanced datasets with deep models.
method DRAGON is a late-fusion architecture that corrects bias towards frequent classes and fuses class-descriptions to improve tail-class accuracy.
result DRAGON outperforms state-of-the-art models on new benchmarks for long-tail learning with class descriptors.
New architectures improve KANs, making them more interpretable and accurate.
problem Improving Kolmogorov-Arnold networks while maintaining interpretability.
method Overprovisioned architectures combined with sparsification, deep supervision, and depth selection, optimized with a minimum description length objective.
result Combining sparsification with depth selection achieves competitive or superior accuracy while discovering smaller models.
Paper evaluates using app images for classification, improving accuracy.
problem Improving app classification accuracy when text descriptions are missing or inadequate.
method Used OCR, pic2vec, captionbot.ai, and object detection to convert images into text or vectors for classification.
result Improved classification accuracy of 96% for some app categories when images are added.
Model predicts price polarity of real estate properties using website information.
problem Predicting price polarity of real estate properties.
method Uses doc2vec and xgboost to learn correlations between price and text descriptions of properties.
result Text descriptions provide slightly higher accuracy than features alone.
Paper uses BERT to assess P2P borrowers' credit risk from loan descriptions.
problem Information asymmetry in P2P lending due to lack of borrower data.
method Fine-tunes BERT on Lending Club dataset to generate risk scores from loan descriptions.
result BERT-generated risk scores improve XGBoost classifier's performance in loan granting.
Improved satellite image captions enhance descriptiveness without large models.
problem Extracting meaningful text from satellite imagery.
method Evaluated seven models on a large benchmark, extended vocabulary, and introduced a novel confusion matrix.
result Reduced model size by 100x without sacrificing accuracy, offering new deployment opportunities.
A new framework uses text descriptions to improve protein design.
problem Lack of effective methods to incorporate textual descriptions in protein design.
method ProteinDT framework that combines text and protein structural information.
result ProteinDT significantly improves protein design accuracy and performance.
Collaborative filtering is used to recommend items to a user without requiring a knowledge of the item itself and tends to outperform other techniques. However, collaborative filtering suffers from the cold-start problem, which occurs when an item has not yet been rated or a user has not rated any items. Incorporating …
Paper presents a more accurate method for nonparametric density estimation using FMMPL and SIR.
problem Improving nonparametric density estimation for complex datasets.
method Finite mixture model of nonparametric density estimation using sampling importance resampling.
result FMMPL provides more accurate results with less space complexity.
Score based learning (SBL) is a promising approach for learning Bayesian networks in the discrete domain. However, when employing SBL in the continuous domain, one is either forced to move the problem to the discrete domain or use metrics such as BIC/AIC, and these approaches are often lacking. Discretization can have …
SANs use sparse activation functions to compress data representations.
problem Learning meaningful features without considering compression.
method Introduce φ metric, define activation functions, and present SANs.
result SANs achieve small description length and interpretable kernels.
SANs use sparse activation functions to minimize model complexity.
problem Model complexity in unsupervised learning.
method Introduce φ metric, define activation functions, present Sparsely Activated Networks (SANs).
result SANs with selected activation functions have small description length and interpretable kernels.
New accuracy measure Ha improves AI system assessment in clinical practice.
problem Inadequate metrics for assessing AI system performance in clinical settings.
method Introducing H-accuracy (Ha) as a more informative measure.
result H-accuracy is a generalization of balanced accuracy and related to Net Benefit.
DL/FBF improves GPSR solutions by selecting compact, generalising expressions.
problem Overfitting and structural bloat in symbolic regression with genetic programming.
method Description length (DL) and fractional Bayes factor (FBF) criteria for selecting compact, generalising expressions.
result DL/FBF post-selection improves test performance compared to AIC/BIC baseline.
Recurrent neural networks improve time series forecasting accuracy.
problem Time series forecasting is challenging, especially for sequential data.
method A recurrent neural network framework for feature engineering, prediction, and evaluation is presented.
result The LSTM and GRU networks outperform traditional methods in forecasting accuracy.
Deep Belief Networks (DBN) have been successfully applied on popular machine learning tasks. Specifically, when applied on hand-written digit recognition, DBNs have achieved approximate accuracy rates of 98.8%. In an effort to optimize the data representation achieved by the DBN and maximize their descriptive power, re…
Automated radar data labeling using GNSS improves efficiency without sacrificing accuracy.
problem Manual annotation of automotive radar data is time-consuming and error-prone.
method The article introduces an automated system using GNSS to acquire data labels.
result The proposed method provides clear advantages in time savings with minimal data distortion.
The Minimum Description Length (MDL) principle states that the optimal model for a given data set is that which compresses it best. Due to practial limitations the model can be restricted to a class such as linear regression models, which we address in this study. As in other formulations such as the LASSO and forward …
Machine learning predicts Kronecker coefficients with high accuracy.
problem Predicting Kronecker coefficients from tensor products of symmetric group representations.
method Training machine learning models (NN, CNN, GBDT) to classify Kronecker coefficients as zero or non-zero.
result Trained models achieve high accuracy (≈0.98) in classifying Kronecker coefficients. This paper studies fixed sets in ribbon complexes using descriptive proximity spaces.
problem Understanding fixed sets in ribbon complexes within descriptive proximity spaces.
method Introduces descriptive fixed sets and their properties in ribbon complexes, using descriptive proximally continuous maps.
result Establishes that proximal descriptive conjugacy preserves fixed sets in ribbon complexes.
Balancing graph summarization and change detection in streaming data.
problem Balancing compression rate in graph summarization and accuracy in change detection.
method Introducing a probabilistic hierarchical latent variable model and optimizing parameters based on the minimum description length principle to balance the trade-off.
result Guaranteed suppression of Type I error probability (false alarms) in change detection.
S2KAN integrates symbolic primitives into neural network activations for improved interpretability.
problem Training activations in KANs often lack symbolic fidelity, leading to unintelligible models.
method Softly Symbolified Kolmogorov-Arnold Networks (S2KAN) integrates symbolic primitives into training with learnable gates and a Minimum Description Length objective.
result S2KAN discovers interpretable forms when symbolic terms suffice, gracefully degrading to dense splines when necessary.
Automatic understanding of domain specific texts in order to extract useful relationships for later use is a non-trivial task. One such relationship would be between railroad accidents' causes and their correspondent descriptions in reports. From 2001 to 2016 rail accidents in the U.S. cost more than $4.6B. Railroads i…
New method evaluates text-to-image synthesis for realism, variety, and semantic accuracy.
problem Lack of metrics revealing semantic accuracy in text-to-image synthesis.
method Uses Inception network representations and t-SNE visualization for semantic evaluation.
result Classification accuracy of generated images to real images' visual concepts correlates with semantic accuracy.
Using Kirby Calculus, we explicitly pass from Berge's R-R descriptions of ten families of knots with lens space surgeries to surgery descriptions on the minimally twisted five chain link (MT5C). Since the MT5C admits a strong involution, we also give the corresponding tangle descriptions.
FastSGT improves accuracy in BERT-based DST for SGD datasets.
problem Dialog State Tracking in goal-oriented dialogue systems.
method BERT-based model with two carry-over procedures and multi-head attention.
result Significantly improved accuracy compared to baseline model.
BERT learns claim descriptions to identify patent novelty.
problem Identifying novel patent claims among existing documents.
method Training BERT on concatenated claims and descriptions, scoring BERT's output.
result BERT identifies relevant X documents for patent novelty.
A new method avoids overfitting in network reconstruction by using the minimum description length principle.
problem Determining the optimal model complexity in network reconstruction to prevent overfitting.
method Hierarchical Bayesian inference and weight quantization based on the minimum description length principle.
result The method yields increased accuracy in reconstructing both artificial and empirical networks.
Minimum Description Length prevents overfitting in noisy data.
problem Learning from noisy data with overfitting risk.
method Minimum Description Length learning rule with tempered guarantees.
result Tempered agnostic finite sample learning guarantees and asymptotic behavior characterization.
Tensor approach simplifies Euclidean space descriptions.
problem Simplifying tensor descriptions of Euclidean spaces.
method Emphasizes geometric vectors in tensor description.
result Proved integral identities with vector integrands.
Generative grading improves automated feedback for structured problems.
problem Difficulty in providing high-quality feedback on structured assignments.
method Generative descriptions of student cognition, probabilistic programs, and learning to infer feedback.
result Achieved near-human accuracy in grading and feedback across diverse domains.
New method learns convolution-like structures from scratch.
problem Learning convolution-like structures from data.
method Minimum description length principle and β-LASSO algorithm. result Learned architectures achieve state-of-the-art accuracies.
AI-enhanced product embeddings boost demand analysis accuracy.
problem Traditional demand analysis struggles with nuanced product attributes.
method Combining text, images, and tabular data with transformer embeddings for causal inference.
result AI-enhanced embeddings improve sales rank and price predictions.
Support Vector Data Description (SVDD) is a popular outlier detection technique which constructs a flexible description of the input data. SVDD computation time is high for large training datasets which limits its use in big-data process-monitoring applications. We propose a new iterative sampling-based method for SVDD…
Machine-learning of atomic-scale properties amounts to extracting correlations between structure, composition and the quantity that one wants to predict. Representing the input structure in a way that best reflects such correlations makes it possible to improve the accuracy of the model for a given amount of reference …
By obtaining surgery descriptions of knots which lie on the genus one fiber of the trefoil or figure eight knot, we show that these include hyperbolic knots with arbitrarily large volume. These knots admit lens space surgeries and form two families of Berge knots. By way of tangle descriptions we also obtain surgery de…
The paper explores new rules for analyzing label rankings and pairwise preferences.
problem Mining patterns in multi-target relations for label ranking.
method Developed two types of association rules: Label Ranking Association Rules (LRAR) and Pairwise Association Rules (PAR). Conducted sensitivity analysis on similarity measures.
result Both LRAR and PAR show potential in analyzing multi-target relations.
Price and return predictions are limited by economic complexity, not just volatility.
problem Limited accuracy of price and return probability forecasts by Gaussian distributions.
method Analyzes economic reasons behind limitations in predicting price and return statistical moments.
result Predictions of price and return probabilities by Gaussian distributions are inaccurate due to economic complexity.
Unique surgery descriptions found for knots in 3-manifolds.
problem Characterizing and understanding unique surgery descriptions for knots in 3-manifolds.
method Analyzing infinitely many surgeries along knots and hyperbolic L-space knots, proving unique descriptions.
result Infinitely many surgeries along knots have unique descriptions, generalizing the concept of characterizing slopes.
The twisted face-pairing construction of our earlier papers gives an efficient way of generating, mechanically and with little effort, myriads of relatively simple face-pairing descriptions of interesting closed 3-manifolds. The corresponding description in terms of surgery, or Dehn-filling, reveals the twist construct…
Study predicts Euroleague basketball games with simple models, less accurate than crowds.
problem Predicting Euroleague basketball games with machine learning.
method Extracted features from Euroleague data, applied supervised machine learning techniques.
result Simple machine learning models achieve accuracy of less than 67% on test sets, outperformed by crowds.
A new model improves relation extraction accuracy through relation-gated adversarial learning.
problem Relation extraction from sentences is challenging due to expensive human annotation and noisy distant supervision.
method Proposes relation-gated adversarial learning for relation extraction, extending domain adaptation methods.
result The model outperforms previous domain adaptation methods and improves accuracy of distance supervised relation extraction.
Unified understanding of neural networks on group operations verified.
problem Understanding and verifying neural networks trained on group operations.
method Investigated one-hidden-layer neural networks trained on binary operation of finite groups, revealing structure and providing a compact proof of model performance.
result Verified explanation applies to a large fraction of networks trained on the symmetric group S5, providing a >=95% accuracy bound for 45% of models.
Study compares BERT and XLNet for multi-class categorization of product descriptions.
problem Robustness of multi-class categorization using pre-trained contextualized language models.
method Fine-tuning BERT and XLNet on Amazon product data for multi-class classification.
result Performance decreases linearly with the number of class labels, with BERT consistently outperforming XLNet.
Chart descriptions are a graphic method to describe monodromy representations of various topological objects. Here we introduce a chart description for hyperelliptic Lefschetz fibrations, and show that any hyperelliptic Lefschetz fibration can be stabilized by fiber-sum with certain basic Lefschetz fibrations.