TFCheck detects training issues in ML programs using TensorFlow.
problem Training programs often contain inconsistencies and bugs.
method Developed a TensorFlow library (TFCheck) with verification routines.
result TFCheck successfully detects training issues in ML code.
Non-experts design prediction tasks and train models on the data they collect.
problem Leveraging non-expert contributions in AI prediction tasks.
method Crowdsourcing platform for task design, automatic model training and evaluation.
result Non-experts can design useful prediction tasks and train models on the data they collect.
Myia compiler optimizes ML models with efficient AD for array programming.
problem Efficient automatic differentiation for array programming in ML.
method Introduces a new graph-based IR that supports function calls, higher-order functions, and recursion.
result Myia compiler enables efficient AD using source transformation without a tape, supporting higher-order derivatives.
MLtuner automates tuning machine learning parameters for better performance.
problem Manual tuning of machine learning parameters is error-prone and requires domain knowledge.
method Snapshotting, branching, and optimization-guided online trial-and-error.
result MLtuner finds and re-tunes parameters robustly and efficiently for various ML applications.
New approach for active learning in overparameterized models.
problem Efficiently labeling datasets in machine learning.
method MaxiMin Active Learning for nonparametric or overparameterized models.
result Automatically identifies decision boundaries and data clusters.
AVATAR uses a surrogate model to quickly evaluate ML pipelines, saving time and resources.
problem Time-consuming evaluation of ML pipelines limits exploration of complex models.
method AVATAR employs a surrogate model to assess pipeline validity without execution.
result AVATAR accelerates ML pipeline evaluation, improving efficiency in complex scenarios.
DeepLine automates ML pipeline generation using reinforcement learning.
problem Automatic generation of end-to-end ML pipelines combining multiple algorithms.
method Deep Reinforcement Learning with hierarchical actions filtering.
result DeepLine outperforms state-of-the-art approaches in accuracy and computational cost.
Machine learning builds personalized pediatric abdominal phantoms.
problem Lack of individualized phantoms for radiation therapy studies.
method Combining imaging and machine learning to automatically build phantoms.
result Automatically constructed phantoms more accurately represent patient anatomy.
Paper evaluates ML's resilience in detecting ransomware.
problem Resilience of ML algorithms for ransomware detection.
method Used GAN to generate dynamic features to test ML models.
result ML models degrade in performance when faced with GAN-generated samples.
Differential ML combines AAD with ML for fast, accurate financial derivatives pricing and risk management.
problem Computational bottlenecks in financial derivatives risk management.
method Novel algorithms using automatic adjoint differentiation (AAD) for training fast, accurate approximations in real-time.
result Convergence guarantees for fast, accurate pricing and risk approximations for arbitrary derivatives instruments.
Vamsa tracks data usage in Python scripts for ML models.
problem Automatically tracking data used in ML model training.
method Modular system that extracts provenance from Python scripts.
result Vamsa achieves high precision and recall in tracking data usage.
This paper uses ML to identify prey handling in seals.
problem Automatically classify prey handling activity in seals for monitoring.
method Developed and compared three ML algorithms: Input Delay Neural Networks, Support Vector Machines, and Echo State Networks.
result Echo State Networks outperformed other algorithms in terms of accuracy and F1score.
New dataset for urban point cloud segmentation and classification.
problem Lack of high-quality urban point cloud datasets for machine learning.
method Acquired by Mobile Laser Scanning (MLS), post-processed and labeled.
result Dataset can be used for learning classification and segmentation algorithms.
Auto-ML framework tackles data drift using GBDT and incremental learning.
problem Data distribution changes over time, reducing model performance.
method GBDT and Incremental learning for handling data drift.
result Effective solution for data drift with robust performance.
Web browser autofill predicts form field labels for convenience.
problem Predicting form field labels for autofill in web browsers.
method Machine learning solution implemented as a web service using Azure ML Studio.
result Improved form field label prediction for autofill.
Tribuo integrates ML models with provenance in Java.
problem Tracking and ensuring ML models behave appropriately as they grow in number and complexity.
method Integrates model training, inference, type-safety, runtime checking, and automatic provenance recording into a single Java library.
result Automatic recording of full processing pipeline and training details inside the model object.
ease.ml enables multiple research groups to share resources for machine learning tasks.
problem Resource allocation in a multi-tenant machine learning environment.
method Formalized multi-tenant model selection problem, developed a novel algorithm combining multi-armed bandits and Bayesian optimization.
result The proposed algorithm achieves up to 9.8x faster global quality for all users compared to heuristics.
CodeReef enables sharing ML models across platforms efficiently.
problem Sharing and deploying ML models across different systems efficiently.
method Developed an open platform to share ML components, automate deployment, and benchmark models.
result Demonstrated efficient deployment and benchmarking of ML models across diverse platforms.
MARVIN offers an open ML environment for automated primitive annotation and execution.
problem Automated machine learning primitive annotation and execution.
method Web-based Python application with Docker containers on Kubernetes.
result Over 400 datasets and challenges from various ML domains.
Automatically identifies RRLyrae stars from VVV survey data.
problem Classifying RRLyrae stars from a large dataset of light curves.
method Developed an automatic ML-based procedure to identify RRLs, using features like period and intensity, and pseudo-colors.
result Constructed an ensemble classifier with Recall of 0.48 and Precision of 0.86 over 15 tiles.
System detects overfitting in ML apps, improving quality and efficiency.
problem Overfitting in ML applications during continuous development.
method ease. ml/meter system for automated overfitting detection and measurement.
result Probabilistic overfitting signals for developers to take actions.
Clarifies the various fairness definitions in ML.
problem Addressing fairness in ML with different definitions.
method Analyzes and clarifies the differences between fairness definitions.
result Provides a clearer understanding of fairness definitions in ML.
Machine learning speeds up GPR simulations.
problem Computational demands of simulating practical GPR problems.
method Automatic ML-based forward solver framework using gprMax.
result Near-real-time GPR simulations achieved.
CK simplifies ML model deployment and reproducibility with open APIs and DevOps.
problem Making ML models reproducible and deployable across different environments.
method Decompose complex systems into reusable sub-components with unified APIs and DevOps principles.
result Automatically co-design and optimize ML models for speed, accuracy, energy, and size.
We present an asymptotic analysis of Viterbi Training (VT) and contrast it with a more conventional Maximum Likelihood (ML) approach to parameter estimation in Hidden Markov Models. While ML estimator works by (locally) maximizing the likelihood of the observed data, VT seeks to maximize the probability of the most lik…
Paper outlines a system for ML models to learn continuously from evolving data.
problem Managing ML models in environments where data evolves.
method Describes a reference architecture for self-maintaining systems.
result Proposes a reference architecture for continual AutoML.
A framework assesses the quality of crowdsourced weather data.
problem Quality control and assessment of crowdsourced weather data from third-party stations.
method Proposes a simple, scalable, and interpretable AI/Stats/ML framework to assess TPAWS data.
result Demonstrates the performance of the framework using synthetic and real data.
Automates translating natural language to Verilog for digital design.
problem Manual translation of natural language specifications to Verilog is time-consuming and error-prone.
method Fine-tuned GPT-2 to derive Verilog from English, using a dataset of design tasks.
result GPT-2 achieved 94.8% correct translation across simple and abstract design tasks.
A review of ML and DL for ecological data analysis.
problem Understanding the strengths and limitations of ML and DL in ecological research.
method Historical overview, algorithm families, differences, universal principles, and emerging trends.
result ML and DL excel in prediction tasks but are still debated for causal inference.
Defends against ML inference attacks using adversarial examples.
problem Automated inference attacks using ML classifiers pose privacy and security threats.
method Turns ML classifier vulnerabilities into defenses by adding adversarial noise to public data.
result Adversarial examples can mislead ML classifiers and protect private data.
Julia programs and ML models are compiled and offloaded to Google Cloud TPUs.
problem Efficiently compiling and executing machine learning models on Google Cloud TPUs.
method Developed a method to compile and offload Julia programs and ML models to Google Cloud TPUs using the Google XLA compiler.
result Successfully fused a VGG19 model into a single TPU executable, achieving 0.23s evaluation time on a batch of 100 images.
The paper proposes a method to evaluate ML models for subjective inference, focusing on sentence toxicity.
problem Bias in ML models for subjective inference, especially in real-life applications.
method Proposes a list of specifications to evaluate ML models for subjective inference, illustrated with a sentence toxicity example.
result Demonstrates the importance of considering subjectivity and bias in evaluating ML models.
Insect-inspired neural nets boost machine learning accuracy with limited data.
problem Difficulty of machine learning with scarce training data.
method Deployed MothNet, a computational model of insect olfactory network, as a feature generator.
result Cyborgs improved test set accuracy by 6% to 33% compared to baseline ML methods.
A ML-based method reconstructs 3D organ doses from 2D radiographs for pediatric abdominal radiotherapy.
problem Reconstructing detailed 3D dose distributions for childhood cancer survivors using limited 2D radiographs.
method Surrogate-free ML approach using 142 abdominal planning CTs, 300 artificial plans, and evolutionary algorithm.
result Accurate 3D dose reconstructions with MAEs ≤ 1.7 Gy for edge organs, validated on independent dataset.
Dataset of Bose-Einstein condensates images aids ML in many-body physics.
problem Understanding solitons in Bose-Einstein condensates.
method Machine learning (ML) framework with convolutional neural networks and physics-informed classifiers.
result Automatic labeling of solitonic excitations in experimental images.
FeatureEnVi aids in feature engineering with visual analytics.
problem Insufficient support for feature engineering in visual analytics tools.
method Stepwise selection and semi-automatic extraction approaches.
result Extracts heavily engineered features evaluated by multiple metrics.
A new framework tackles CASH problem with alternating optimization and Rising Bandits.
problem Efficiently solving the Combined Algorithm Selection and Hyperparameter optimization (CASH) problem.
method Alternating optimization framework using BO for HPO and Rising Bandits for algorithm selection.
result Demonstrated superiority over competitive baselines in extensive experiments.
Bayesian optimization framework for fair machine learning models.
problem Bias in machine learning models and lack of adaptability of fairness techniques.
method General constrained Bayesian optimization framework.
result BO can optimize ML models for fairness without model-specific constraints.
autoBagging learns to rank bagging workflows for better ML performance.
problem Finding the best bagging workflow for each dataset.
method Metalearning and learning to rank to automatically rank bagging workflows.
result autoBagging outperforms Average Rank and achieves results not statistically different from an ideal model.
Machine learning improves cybersecurity by learning from data.
problem Designing effective detection algorithms for cyber threats.
method Machine learning algorithms to learn from security data.
result ML algorithms can improve threat hunting and remediation.
Most modern supervised statistical/machine learning (ML) methods are explicitly designed to solve prediction problems very well. Achieving this goal does not imply that these methods automatically deliver good estimators of causal parameters. Examples of such parameters include individual regression coefficients, avera…
MGD improves ML training efficiency and accuracy.
problem Optimizing large-scale ML model training configurations.
method Metagradient descent and smooth model training.
result Significantly improved model performance and learning rate schedules.
ADS automates data preparation for ML/AI, reducing human effort.
problem Manual and time-consuming data preparation for ML/AI.
method Data-driven approach using statistics and ML.
result ADS automates data exploration and processing steps.
Develops ACE to automatically identify meaningful concepts from neural network predictions.
problem Challenges in interpreting feature importance scores for machine learning models.
method Proposes concept-based explanation principles and develops ACE algorithm to extract visual concepts.
result Demonstrates ACE discovers human-meaningful, coherent concepts for neural network predictions.
Graph Neural Networks improve machine learning on relational databases.
problem Training machine learning models on relational databases requires costly data extraction and feature engineering.
method Uses Graph Neural Networks to extract features from relational databases.
result Outperforms state-of-the-art automatic feature engineering methods.
Automated AL improves ML potentials for organic molecules, reducing training data by 90%.
problem Developing accurate and transferable ML potentials for molecular energetics.
method Active learning via Query by Committee (QBC) to sample chemical space.
result AL-based potentials achieve similar accuracy with 10-25% of data, outperforming ANI-1.
The study assesses ML model robustness under worst-case subpopulations.
problem ML model performance degradation under non-training population.
method Two-stage estimation procedure for evaluating worst-case robustness over subpopulations.
result The method certifies model robustness and prevents unreliable deployments.
This paper surveys and benchmarks AutoML frameworks.
problem Reducing the need for data scientists in building machine learning applications.
method Survey and benchmark of popular AutoML frameworks on real data sets.
result Evaluation of 137 data sets from established AutoML benchmark suits.