Universal learning machine is a theory trying to study machine learning from mathematical point of view. The outside world is reflected inside an universal learning machine according to pattern of incoming data. This is subjective pattern of learning machine. In [2,4], we discussed subjective spatial pattern, and estab…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “learning patterns”
While Multiple Instance (MI) data are point patterns -- sets or multi-sets of unordered points -- appropriate statistical point pattern models have not been used in MI learning. This article proposes a framework for model-based MI learning using point process theory. Likelihood functions for point pattern data derived …
Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shiftcs.LG
TFPS improves time series forecasting by learning pattern-specific experts.
problem Challenges in forecasting time series data with varying patterns across segments.
method Dual-domain encoder, subspace clustering, pattern-specific experts.
result Significantly improved forecasting accuracy, especially in long-term forecasting.
A cornerstone of human statistical learning is the ability to extract temporal regularities / patterns from random sequences. Here we present a method of computing pattern time statistics with generating functions for first-order Markov trials and independent Bernoulli trials. We show that the pattern time statistics c…
Video sequences contain rich dynamic patterns, such as dynamic texture patterns that exhibit stationarity in the temporal domain, and action patterns that are non-stationary in either spatial or temporal domain. We show that a spatial-temporal generative ConvNet can be used to model and synthesize dynamic patterns. The…
In the field of exploratory data mining, local structure in data can be described by patterns and discovered by mining algorithms. Although many solutions have been proposed to address the redundancy problems in pattern mining, most of them either provide succinct pattern sets or take the interests of the user into acc…
In this paper, we investigate the multi-variate sequence classification problem from a multi-instance learning perspective. Real-world sequential data commonly show discriminative patterns only at specific time periods. For instance, we can identify a cropland during its growing season, but it looks similar to a barren…
Feature Learning for Nonlinear Dimensionality Reduction toward Maximal Extraction of Hidden Patternscs.LG
FEALM learns features for better nonlinear DR of hidden patterns.
problem DR misses important patterns on distorted manifolds.
method FEALM generates optimized projections using an optimization algorithm and neighbor-shape dissimilarity.
result FEALM captures important patterns on hidden manifolds.
In many complex dynamical systems, artificial or natural, one can observe self-organization of patterns emerging from local rules. Cellular automata, like the Game of Life (GOL), have been widely used as abstract models enabling the study of various aspects of self-organization and morphogenesis, such as the emergence …
MPPN network improves long-term time series forecasting accuracy.
problem Inaccurate long-term time series forecasting due to noise and lack of interpretability.
method MPPN network constructs context-aware multi-resolution semantic units and employs multi-periodic pattern mining and channel adaptive module.
result MPPN significantly outperforms state-of-the-art methods on nine real-world benchmarks.
Acquisition of Magnetic Resonance Imaging (MRI) scans can be accelerated by under-sampling in k-space (i.e., the Fourier domain). In this paper, we consider the problem of optimizing the sub-sampling pattern in a data-driven fashion. Since the reconstruction model's performance depends on the sub-sampling pattern, we c…
As machine learning is increasingly used to make real-world decisions, recent research efforts aim to define and ensure fairness in algorithmic decision making. Existing methods often assume a fixed set of observable features to define individuals, but lack a discussion of certain features not being observed at test ti…
A textbook on machine learning explaining patterns, predictions, and actions.
problem Understanding patterns in data for predictions and actions.
method Explains foundations of decision making, representation, optimization, and generalization.
result Equips readers with tools to reason about actions and their consequences.
This study evaluates the performances of CNN and LSTM for recognizing common charts patterns in a stock historical data. It presents two common patterns, the method used to build the training set, the neural networks architectures and the accuracies obtained.
Candlesticks are graphical representations of price movements for a given period. The traders can discovery the trend of the asset by looking at the candlestick patterns. Although deep convolutional neural networks have achieved great success for recognizing the candlestick patterns, their reasoning hides inside a blac…
Transformers learn to integrate information from past positions incrementally, specializing heads in distinct patterns.
problem How transformers learn to integrate information from multiple past positions with varying statistical significance.
method High-order Markov chain task, incremental learning, sparse attention patterns, simplified differential equations, stage-wise convergence, early stopping as regularizer.
result Transformers learn to specialize heads in distinct patterns, shifting from competitive to cooperative learning dynamics.
Parallel Learning by Multitasking Neural Networkscond-mat.dis-nn
New neural network can learn multiple patterns at once.
problem Learning multiple patterns simultaneously in neural networks.
method Multitasking Hebbian Network (MHN) for parallel learning of sparse data-sets.
result MHN can handle multiple patterns hierarchically or in parallel, depending on dilution.
PSEUDo learns patterns in multivariate time series with locality-sensitive hashing and relevance feedback.
problem Efficient pattern detection in large, multi-track sequential data with high variance and lack of ground truth.
method Query-aware locality-sensitive hashing for feature learning, sub-linear training and inference time.
result PSEUDo achieves sub-linear time efficiency for pattern modeling and comparison of 10,000 multivariate time series.
Structured latent attribute models (SLAMs) are a special family of discrete latent variable models widely used in social and biological sciences. This paper considers the problem of learning significant attribute patterns from a SLAM with potentially high-dimensional configurations of the latent attributes. We address …
A streaming GNN model tackles continual learning for updating node representations in real-time.
problem Learning new patterns in streaming graph data while maintaining existing patterns.
method Designing an approximation algorithm for pattern detection, combining data replaying and model regularization.
result Our model efficiently updates model parameters and achieves comparable performance to model retraining.
TrustNet robustly learns noise patterns from trusted data to improve weakly-supervised classification.
problem Robustness to label noise in weakly-supervised learning.
method TrustNet learns noise patterns from trusted data, then trains a robust classifier using these patterns.
result TrustNet outperforms state-of-the-art methods in robustness to various noise patterns.
Pattern recognition and machine learning are becoming integral parts of algorithms in a wide range of applications. Different algorithms and approaches for machine learning include different tradeoffs between performance and computation, so during algorithm development it is often necessary to explore a variety of diff…
A novel framework interprets driving patterns using Action phases clustering.
problem Challenges in comprehending driving heterogeneity from underlying behavior mechanisms.
method Resampling and Downsampling Method (RDM) followed by iterative clustering calibration.
result Six driving patterns identified in real-world datasets, revealing dynamic nature of driving.
We describe two recently proposed machine learning approaches for discovering emerging trends in fatal accidental drug overdoses. The Gaussian Process Subset Scan enables early detection of emerging patterns in spatio-temporal data, accounting for both the non-iid nature of the data and the fact that detecting subtle p…
Electroencephalography (EEG) is a method to record the electrical signals in the brain. Recognizing the EEG patterns in the sleeping brain gives insights into the understanding of sleeping disorders. The dataset under consideration contains EEG data points associated with various physiological conditions. This study at…
A new method for handling missing values in data.
problem Handling missing values in machine learning models.
method Sharing pattern submodels with sparsity-inducing regularization.
result Sharing pattern submodels provide robust predictions and maintain/improve pattern submodel performance.
This paper formalizes a latent variable inference problem we call {\em supervised pattern discovery}, the goal of which is to find sets of observations that belong to a single ``pattern.'' We discuss two versions of the problem and prove uniform risk bounds for both. In the first version, collections of patterns can be…
Convolutional dictionary learning (CDL) estimates shift invariant basis adapted to multidimensional data. CDL has proven useful for image denoising or inpainting, as well as for pattern discovery on multivariate signals. As estimated patterns can be positioned anywhere in signals or images, optimization techniques face…
Paper develops new patterns for unique matrix completions.
problem Developing unique completions for non-random matrix patterns.
method Formulated low-rank matrix completion using Plucker coordinates.
result Provides two families of patterns for any rank.
A representative model in integrative analysis of two high-dimensional correlated datasets is to decompose each data matrix into a low-rank common matrix generated by latent factors shared across datasets, a low-rank distinctive matrix corresponding to each dataset, and an additive noise matrix. Existing decomposition …
We aim to model unknown file processing. As the content of log files often evolves over time, we established a dynamic statistical model which learns and adapts processing and parsing rules. First, we limit the amount of unstructured text by focusing only on those frequent patterns which lead to the desired output tabl…
Meta-learning predicts stock trading volumes by learning from each stock's unique patterns.
problem Predicting trading volumes for different stocks using a universal model.
method Dual-process meta-learning framework that learns common patterns with a meta-learner and specific patterns with stock-dependent parameters.
result Improves performance of various baseline models in volume predictions.
Point patterns are sets or multi-sets of unordered elements that can be found in numerous data sources. However, in data analysis tasks such as classification and novelty detection, appropriate statistical models for point pattern data have not received much attention. This paper proposes the modelling of point pattern…
UDA learns target domain from unlabeled data via source knowledge transfer.
problem Learning unlabeled target domain data.
method Transferring both source knowledge and target-relatedness.
result Improves UDA performance by simultaneous knowledge transfer.
Label noise may affect the generalization of classifiers, and the effective learning of main patterns from samples with noisy labels is an important challenge. Recent studies have shown that deep neural networks tend to prioritize the learning of simple patterns over the memorization of noise patterns. This suggests a …
PbP strategy improves logistic model prediction with missing values.
problem Predicting with missing inputs in logistic models.
method Pattern-by-Pattern (PbP) strategy for logistic models with missing values.
result PbP accurately approximates Bayes probabilities under GPMM across various missing data scenarios.
In this paper, we show that standard feed-forward and recurrent neural networks fail to learn abstract patterns based on identity rules. We propose Relation Based Pattern (RBP) extensions to neural network structures that solve this problem and answer, as well as raise, questions about integrating structures for induct…
GraphDETR detects subgraphs in large graphs using deep learning.
problem Detecting subgraphs in large graphs efficiently and accurately.
method Formulates subgraph detection as a set prediction problem using GraphDETR, a deep learning framework.
result GraphDETR can detect diverse patterns in large graphs, achieving strong performance on molecular functional group detection.
We analyze expenditure patterns of discretionary funds by Brazilian congress members. This analysis is based on a large dataset containing over million expenses made publicly available by the Brazilian government. This dataset has, up to now, remained widely untouched by machine learning methods. Our main contribut…
Paper proposes TRA to learn multiple stock trading patterns.
problem Inconsistent i.i.d. assumption limits stock prediction performance.
method TRA architecture with Optimal Transport for pattern assignment.
result Improves information coefficient (IC) by 0.04-0.06 compared to baselines.
Extends quadratic loss for SVM and deep learning to improve pattern correlation.
problem Improving generalization in supervised binary classification and regression tasks.
method Extends quadratic loss, restarts from problem (8) in [3], proposes new algorithms, uses multiple kernel learning.
result Comparable results with standard losses and parameterized quadratic loss.
Supervised, semi-supervised, and unsupervised learning estimate a function given input/output samples. Generalization of the learned function to unseen data can be improved by incorporating side information into learning. Side information are data that are neither from the input space nor from the output space of the f…
Graph Neural Networks improve financial time series forecasting accuracy.
problem Forecasting univariate financial time series with statistical significance.
method Introducing the Time-Geometric model combining geometric and temporal patterns.
result Statistically significant improvements in forecasting accuracy through geometric patterns.
A modern Hopfield network improves deep learning with better memory and attention.
problem Improving memory and attention mechanisms in deep learning.
method Introducing a new Hopfield network with continuous states and a novel update rule.
result The new Hopfield network can store and retrieve patterns efficiently with low errors.
Quantum-enhanced barcode decoding and pattern recognition outperforms classical methods.
problem Improving barcode decoding and pattern recognition using quantum entanglement.
method Quantum hypothesis testing applied to barcode decoding and pattern recognition using entangled quantum sources and measurements.
result Quantum-enhanced methods outperform classical coherent-state strategies for barcode data decoding and classification.
Predicts COVID-19 spread using dictionary learning and online NMF.
problem Limited daily case data for accurate prediction.
method Joint dictionary learning and online NMF for short evolution instances.
result Learned dictionary patterns improve predictions over time.
The paper proposes a new algorithm to select subsets of training data for better accuracy and explainability.
problem Tackles the challenge of balancing accuracy and explainability in pattern recognition.
method Identifies multiple subsets with simple local patterns by clustering similar instances.
result The sub-setting algorithm outperformed traditional decision trees by 15% on the international stroke dataset.
Enhanced deep learning model forecasts household leverage series accurately.
problem Forecasting household leverage series due to complex temporal-spatial dynamics.
method TSEN model with multiple RNN-based layers and an attention layer.
result Captures temporal-spatial dynamics and provides more accurate predictions.