Data science enhances knot theory by analyzing invariant relations.
problem Understanding the complex relations between knot invariants.
method Topological data analysis applied to knot theory.
result New insights into long-standing conjectures about knots.
ALPODS AI diagnoses high-dimensional biomedical data with human-understandable explanations.
problem AI decisions in high-dimensional biomedical data are not explainable to humans.
method ALPODS method classifies data based on clusters and generates fuzzy reasoning rules.
result ALPODS provides understandable explanations for AI diagnoses.
Software helps teach latent variable methods in multivariate data analytics.
problem Challenges in understanding multivariate data analytics for students.
method Interactive software for comparing latent variable methods.
result Builds intuition on choosing methods and interpreting coefficients.
In an attempt to gather a deeper understanding of how convolutional neural networks (CNNs) reason about human-understandable concepts, we present a method to infer labeled concept data from hidden layer activations and interpret the concepts through a shallow decision tree. The decision tree can provide information abo…
Study identifies negative data externalities affecting model performance on specific groups.
problem Negative data externalities on group performance in machine learning models.
method Characterized and detected data-model inefficiencies, focusing on specific types of externalities.
result Negative data externalities can lower model performance on specific sub-groups, even with larger datasets.
Capsule networks improve temporal data understanding, achieving 96.21% ECG accuracy.
problem Improving temporal data understanding with capsule networks.
method Generated capsules along temporal and channel dimensions, learning contrasting relationships.
result Achieved 96.21% accuracy on ECG signal beat categories, surpassing state-of-the-art.
Dependent MMD coresets help compare multiple related datasets.
problem Comparing multiple related datasets for insights into model generalization.
method Dependent MMD coresets for collections of datasets.
result Dependent MMD coresets facilitate comparison and understanding of multiple related datasets.
This work proposes xGEMs or manifold guided exemplars, a framework to understand black-box classifier behavior by exploring the landscape of the underlying data manifold as data points cross decision boundaries. To do so, we train an unsupervised implicit generative model -- treated as a proxy to the data manifold. We …
Many modern Artificial Intelligence (AI) systems make use of data embeddings, particularly in the domain of Natural Language Processing (NLP). These embeddings are learnt from data that has been gathered "from the wild" and have been found to contain unwanted biases. In this paper we make three contributions towards me…
This is a lecture note for the course DS-GA 3001 <Natural Language Understanding with Distributed Representation> at the Center for Data Science , New York University in Fall, 2015. As the name of the course suggests, this lecture note introduces readers to a neural network based approach to natural language understand…
Linear models can grok without understanding, improving generalization.
problem Understanding the phenomenon of grokking in linear models.
method Analytical and numerical derivation of training and generalization dynamics in linear networks.
result Grokking can occur in linear networks without reaching understanding, and its timing depends on various parameters.
Develops a logifold structure for understanding datasets.
problem Understanding and classifying complex datasets.
method Local-to-global approach using measure-theoretical models.
result Improves accuracy in data classification problems.
We perform topological data analysis on the internal states of convolutional deep neural networks to develop an understanding of the computations that they perform. We apply this understanding to modify the computations so as to (a) speed up computations and (b) improve generalization from one data set of digits to ano…
Gen AI improves document understanding but not data analysis in public sector tasks.
problem Understanding the impact of Gen AI on public sector tasks.
method Pre-registered field experiment comparing Gen AI to control group performance.
result Mixed results: Gen AI improves document understanding but not data analysis.
Then detection and identification of extreme weather events in large-scale climate simulations is an important problem for risk management, informing governmental policy decisions and advancing our basic understanding of the climate system. Recent work has shown that fully supervised convolutional neural networks (CNNs…
Study finds transparency and model performance metrics increase trust in AutoML systems.
problem Understanding what information influences trust in AutoML systems.
method Three studies: qualitative interviews, controlled experiment, and card-sorting task.
result Transparency and model performance metrics are most important for establishing trust in AutoML systems.
This paper proposes a new method for an optimized mapping of temporal variables, describing a temporal stream data, into the recently proposed NeuCube spiking neural network architecture. This optimized mapping extends the use of the NeuCube, which was initially designed for spatiotemporal brain data, to work on arbitr…
Machine learning (ML) algorithms and machine learning based software systems implicitly or explicitly involve complex flow of information between various entities such as training data, feature space, validation set and results. Understanding the statistical distribution of such information and how they flow from one e…
Interpole learns transparent decision-making policies from data.
problem Understanding human decision-making in opaque environments.
method Interpole combines belief-update and belief-action mapping estimation.
result Interpole provides interpretable models of decision-making behavior.
Paper improves natural language understanding with less data using a new training method.
problem Limited data hinders performance of small models in natural language tasks.
method Generation-Distillation: uses large finetuned models to generate new training data and distill knowledge into smaller models.
result Achieves comparable performance to BERT with 300x fewer parameters and outperforms prior distillation methods.
In many recent applications, data is plentiful. By now, we have a rather clear understanding of how more data can be used to improve the accuracy of learning algorithms. Recently, there has been a growing interest in understanding how more data can be leveraged to reduce the required training runtime. In this paper, we…
This paper provides a guide to feature importance methods for better scientific inference.
problem Limited understanding of data-generating process due to opaque ML model mechanisms.
method Comprehensive review and new proofs of global feature importance methods.
result Facilitates a thorough understanding and concrete recommendations for FI methods.
This review covers learning under concept drift, including detection, understanding, and adaptation.
problem Unforeseeable changes in data distribution over time impact machine learning performance.
method Reviews and analyzes methodologies and techniques for concept drift detection, understanding, and adaptation.
result Establishes a framework for learning under concept drift with three main components.
Transformers learn topic structure through embedding and attention mechanisms.
problem Understanding how transformers capture semantic structure in text.
method Combination of mathematical analysis and experiments on Wikipedia and synthetic data.
result Embedding and attention layers encode topic structure in transformers.
FinALBERT predicts stock prices using labelled Stocktwits data.
problem Efficient stock price prediction with limited labelled datasets.
method FinALBERT is an ALBERT-based model trained on labelled Stocktwits data for financial text classification.
result FinALBERT achieves optimal results in predicting stock price changes.
NNs accurately predict energy eigenvalues and other physical phenomena in 1D quantum mechanics.
problem Understanding how neural networks interpret physics.
method Training NNs to predict energy eigenvalues from potentials and testing their ability to generalize.
result NNs can predict physical phenomena not learned during training, indicating a new way of understanding physics.
New methods improve brain data analysis from fMRI datasets.
problem Simplified brain models from correlational values are insufficient.
method Deep learning and geometric deep learning techniques.
result Improved predictive spatio-temporal brain data representation.
Simplified equation predicts model sensitivity to data.
problem Understanding model sensitivity to training data is challenging and costly.
method Derived using Bayesian principles, the Memory-Perturbation Equation (MPE) unifies and generalizes existing sensitivity measures.
result Empirical results show sensitivity estimates during training can predict generalization on unseen test data.
Quantum models generalize well with little data, challenging traditional generalization theories.
problem Quantum machine learning models generalize well with few data, contradicting traditional theories.
method Systematic randomization experiments and theoretical constructions.
result Quantum neural networks can fit random states and labels, defying current generalization measures.
This paper explains how transformers learn from unstructured data in ICL.
problem Understanding how transformers learn from unstructured data in in-context learning.
method A simple transformer model with one or two attention layers and positional encoding is used to study the role of each component in ICL.
result A transformer with two attention layers and a look-ahead attention mask can learn from unstructured data.
ZeroSCROLLS benchmarks zero-shot natural language understanding over long texts.
problem Evaluate natural language understanding models over long texts without training data.
method Adapt six tasks from SCROLLS benchmark and add four new datasets, including novel aggregation tasks.
result Claude outperforms ChatGPT, and GPT-4 achieves highest average score.
Meta learning works well with overparameterized models, a phenomenon called 'benign overfitting'.
problem Understanding why overparameterized models perform well in few-shot learning.
method Analyzed the generalization performance of gradient-based meta learning with an overparameterized meta linear regression model.
result Demonstrated that overparameterized meta learning can still generalize well, a phenomenon called 'benign overfitting'.
CERT improves language understanding by contrastively learning sentence-level semantics.
problem Lack of sentence-level semantics in existing pretraining tasks.
method Contrastive self-supervised learning at the sentence level using back-translation augmentations.
result CERT outperforms BERT on 7 out of 11 GLUE benchmark tasks, achieving the same performance as BERT on 2 tasks.
Model integrates multi-view temporal data for better understanding of latent dynamics.
problem Understanding time-dependent heterogeneous properties from multi-view data.
method Generative model using variational autoencoder and recurrent neural network.
result Identifies disentangled latent embeddings across views while accounting for time factor.
New theory explains how equivariant self-supervised learning improves feature extraction.
problem Contrastive learning sacrifices useful features due to invariance to data augmentations.
method Information-theoretic perspective to understand E-SSL's generalization ability.
result Equivariant self-supervised learning creates synergy between equivariant and classification tasks.
Research aims to bridge statistical learning to causal models in AI.
problem Challenges in machine learning and AI related to causality.
method Transition from statistical learning to causal models.
result Progress in AI may require advances in causal modeling.
MILCCI integrates labels across categories for better understanding of multi-trial data.
problem Understanding how labels encode multi-trial observations and disentangling their effects.
method Sparse per-trial decomposition leveraging label similarities within each category.
result MILCCI identifies interpretable components and integrates label information.
Although deep learning techniques have been successfully applied to many tasks, interpreting deep neural network models is still a big challenge to us. Recently, many works have been done on visualizing and analyzing the mechanism of deep neural networks in the areas of image processing and natural language processing.…
The increasing accessibility of data provides substantial opportunities for understanding user behaviors. Unearthing anomalies in user behaviors is of particular importance as it helps signal harmful incidents such as network intrusions, terrorist activities, and financial frauds. Many visual analytics methods have bee…
With online calendar services gaining popularity worldwide, calendar data has become one of the richest context sources for understanding human behavior. However, event scheduling is still time-consuming even with the development of online calendars. Although machine learning based event scheduling models have automate…
Interactive model analysis, the process of understanding, diagnosing, and refining a machine learning model with the help of interactive visualization, is very important for users to efficiently solve real-world artificial intelligence and data mining problems. Dramatic advances in big data analytics has led to a wide …
Graph machine learning lacks a balanced theory, focusing on expressive power and optimization.
problem Insufficient theoretical understanding of GNNs' generalization behavior.
method Develop a balanced theory focusing on expressive power, generalization, and optimization.
result Theoretical advancements need to align with practical success in graph machine learning.
Generalization performance of classifiers in deep learning has recently become a subject of intense study. Deep models, typically over-parametrized, tend to fit the training data exactly. Despite this "overfitting", they perform well on test data, a phenomenon not yet fully understood. The first point of our paper is t…
Understanding learning materials (e.g. test questions) is a crucial issue in online learning systems, which can promote many applications in education domain. Unfortunately, many supervised approaches suffer from the problem of scarce human labeled data, whereas abundant unlabeled resources are highly underutilized. To…
Archetypal analysis helps understand binary data sets.
problem Explaining binary questionnaire data.
method Using archetypal analysis for binary observations.
result The approach contributes to understanding binary data sets.
Improved financial sentiment analysis using simple instruction tuning of LLMs.
problem Lack of accurate financial sentiment analysis by large language models.
method Instruction tuning of general-purpose LLMs with a small portion of financial sentiment data.
result Significant improvement in financial sentiment analysis, especially in complex scenarios.
Advances understanding of neural network generalization via tensor analysis.
problem Understanding the generalizability of deep neural networks.
method Tensor analysis to measure compressibility and generalizability.
result Proposed generalization bound outperforms previous methods, especially for tensor-based networks.
In this paper, we address customer review understanding problems by using supervised machine learning approaches, in order to achieve a fully automatic review aspects categorisation and sentiment analysis. In general, such supervised learning algorithms require domain-specific expert knowledge for generating high quali…