Papers
Wed 17 Feb 2021
140 papers
- Fully General Online Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Towards an AI Coach to Infer Team Mental Model Alignment in HealthcareLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- Risk factor identification for incident heart failure using neural network distillation and variable selection
- Introducing the Hidden Neural Markov Chain framework
- Highly Fast Text Segmentation With Pairwise Markov Chains
- IFoodCloud: A Platform for Real-time Sentiment Analysis of Public Opinion about Food Safety in China
- Performance of Automatic De-identification Across Different Note Types
- Jointly Learning Clinical Entities and Relations with Contextual Language Models and Explicit Context
- Do End-to-End Speech Recognition Models Care About Context?
- Equivariant Spherical Deconvolution: Learning Sparse Orientation Distribution Functions from Spherical Data
- TCN: Table Convolutional Network for Web Table Interpretation
- Enhanced Magnetic Resonance Image Synthesis with Contrast-Aware Generative Adversarial Networks
- NFCNN: Toward a Noise Fusion Convolutional Neural Network for Image Denoising
- FIXME: Enhance Software Reliability with Hybrid Approaches in Cloud
- Grid Cell Path Integration For Movement-Based Visual Object Recognition
- SRDTI: Deep learning-based super-resolution for diffusion tensor MRI
- Towards Adversarial-Resilient Deep Neural Networks for False Data Injection Attack Detection in Power Grids
- Modeling Extremes with d-max-decreasing Neural Networks
- Spacewalker: Rapid UI Design Exploration Using Lightweight Markup Enhancement and Crowd Genetic Programming
- Proactive DP: A Multple Target Optimization Framework for DP-SGD
- Joint Continuous and Discrete Model Selection via Submodularity
- Optimizing Large-Scale Hyperparameters via Automated Learning Algorithm
- Deep Learning Approaches for Forecasting Strawberry Yields and Prices Using Satellite Images and Station-Based Soil Parameters
- Estimate Three-Phase Distribution Line Parameters With Physics-Informed Graphical Learning Method
- Improving Hierarchical Adversarial Robustness of Deep Neural Networks
- BORE: Bayesian Optimization by Density-Ratio Estimation
- An Efficient Diagnosis Algorithm for Inconsistent Constraint Sets
- Domain Impression: A Source Data Free Domain Adaptation Method
- Mobile Computational Photography: A Tour
- One-shot action recognition in challenging therapy scenarios
- Using Distance Correlation for Efficient Bayesian Optimization
- Generalization in Quantum Machine Learning: a Quantum Information Perspective
- BEDS: Bagging ensemble deep segmentation for nucleus segmentation with testing stage stain augmentation
- Automated Detection of Equine Facial Action Units
- Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts
- EEG-based Texture Roughness Classification in Active Tactile Exploration with Invariant Representation Learning Networks
- Adaptive Doubly Robust Estimator from Non-stationary Logging Policy under a Convergence of Average Probability
- Evaluating the Performance of Some Local Optimizers for Variational Quantum Classifiers
- S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration
- Weakly Supervised Learning of Rigid 3D Scene Flow
- Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs
- Sparsely Factored Neural Machine Translation
- An Objective Laboratory Protocol for Evaluating Cognition of Non-Human Systems Against Human Cognition
- Cross-SEAN: A Cross-Stitch Semi-Supervised Neural Attention Model for COVID-19 Fake News Detection
- How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models
- POLA: Online Time Series Prediction by Adaptive Learning Rates
- Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games
- Few-shot Conformal Prediction with Auxiliary Tasks
- Robust Domain-Free Domain Generalization with Class-aware Alignment
- On the Fundamental Limits of Exact Inference in Structured Prediction
- THEaiTRE 1.0: Interactive generation of theatre play scripts
- Towards generalisable hate speech detection: a review on obstacles and solutions
- Differentially Private Correlation Clustering
- MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
- I Want This Product but Different : Multimodal Retrieval with Synthetic Query Expansion
- Online Co-movement Pattern Prediction in Mobility Data
- Bridging the Gap Between Adversarial Robustness and Optimization Bias
- IoTDevID: A Behavior-Based Device Identification Method for the IoT
- A Graph Neural Network to Model Disruption in Human-Aware Robot Navigation
- ShaRF: Shape-conditioned Radiance Fields from a Single View
- Metrical Tagging in the Wild: Building and Annotating Poetry Corpora with Rhythmic Features
- Contrastive Learning Inverts the Data Generating Process
- Genetically Optimized Prediction of Remaining Useful Life
- DESED-FL and URBAN-FL: Federated Learning Datasets for Sound Event Detection
- Crop mapping from image time series: deep learning with multi-scale label hierarchies
- SciDr at SDU-2020: IDEAS -- Identifying and Disambiguating Everyday Acronyms for Scientific Domain
- Dissecting Supervised Contrastive Learning
- Deep Learning for Market by Order Data
- Accelerated Simulations of Molecular Systems through Learning of their Effective Dynamics
- Leveraging Query Resolution and Reading Comprehension for Conversational Passage Retrieval
- Chance-Constrained Active Inference
- Geostatistical Learning: Challenges and Opportunities
- ppAURORA: Privacy Preserving Area Under Receiver Operating Characteristic and Precision-Recall Curves
- Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing
- An asymptotic analysis of probabilistic logic programming, with implications for expressing projective families of distributions
- Predicting Lexical Complexity in English Texts: The Complex 2.0 Dataset
- Muddling Labels for Regularization, a novel approach to generalization
- Group Equivariant Conditional Neural Processes
- Formation of Social Ties Influences Food Choice: A Campus-Wide Longitudinal Study
- Learning Visual Models using a Knowledge Graph as a Trainer
- SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition
- Ego-based Entropy Measures for Structural Representations on Graphs
- Training Aware Sigmoidal Optimizer
- A Dataset and Benchmark for Malaria Life-Cycle Classification in Thin Blood Smear Images
- Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder
- ACTA: A Mobile-Health Solution for Integrated Nudge-Neurofeedback Training for Senior Citizens
- Symmetry Breaking for k-Robust Multi-Agent Path Finding
- Switch Spaces: Learning Product Spaces with Sparse Gating
- Deviation inequalities for stochastic approximation by averaging
- Non-asymptotic approximations of neural networks by Gaussian processes
- Cardiac Motion Modeling with Parallel Transport and Shape Splines
- Preventing Oversmoothing in VAE via Generalized Variance Parameterization
- CheXternal: Generalization of Deep Learning Models for Chest X-ray Interpretation to Photos of Chest X-rays and External Clinical Settings
- Unbiased Estimations based on Binary Classifiers: A Maximum Likelihood Approach
- Decoding EEG Brain Activity for Multi-Modal Natural Language Processing
- A General Framework for the Practical Disintegration of PAC-Bayesian Bounds
- Temporal Memory Attention for Video Semantic Segmentation
- Coupled Feature Learning for Multimodal Medical Image Fusion
- Towards Utility-based Prioritization of Requirements in Open Source Environments
- On the Post-hoc Explainability of Deep Echo State Networks for Time Series Forecasting, Image and Video Classification
All 140
- Open-Retrieval Conversational Machine Reading
- Knowledge discovery from emergency ambulance dispatch during COVID-19: A case study of Nagoya City, Japan
- Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Training
- Rethinking Co-design of Neural Architectures and Hardware Accelerators
- On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method
- Centroid Transformers: Learning to Abstract with Attention
- SWAD: Domain Generalization by Seeking Flat Minima
- LambdaNetworks: Modeling Long-Range Interactions Without Attention
- Leveraging Public Data for Practical Private Query Release
- Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n Parameters
- Data-Driven Logistic Regression Ensembles With Applications in Genomics
- NODE-SELECT: A Graph Neural Network Based On A Selective Propagation Technique
- Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View
- A Discrete-Time Switching System Analysis of Q-learning
- Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning
- Evolving GAN Formulations for Higher Quality Image Synthesis
- DO-GAN: A Double Oracle Framework for Generative Adversarial Networks
- End-to-end lyrics Recognition with Voice to Singing Style Transfer
- Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks
- Self-Triggered Markov Decision Processes
- Outside the Echo Chamber: Optimizing the Performative Risk
- Ensemble Transfer Learning of Elastography and B-mode Breast Ultrasound Images
- Contextual Skipgram: Training Word Representation Using Context Information
- Mode-Assisted Joint Training of Deep Boltzmann Machines
- Re-identification of Individuals in Genomic Datasets Using Public Face Images
- Deep cross-modality (MR-CT) educed distillation learning for cone beam CT lung tumor segmentation
- Recoverability Landscape of Tree Structured Markov Random Fields under Symmetric Noise
- Integrating Pre-trained Model into Rule-based Dialogue Management
- First Target and Opinion then Polarity: Enhancing Target-opinion Correlation for Aspect Sentiment Triplet Extraction
- Active Face Frontalization using Commodity Unmanned Aerial Vehicles
- Intuitively Assessing ML Model Reliability through Example-Based Explanations and Editing Model Inputs
- Separated Proportional-Integral Lagrangian for Chance Constrained Reinforcement Learning
- ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems
- StatEcoNet: Statistical Ecology Neural Networks for Species Distribution Modeling
- Causal Estimation with Functional Confounders
- DeepWalking Backwards: From Embeddings Back to Graphs
- Fast Graph Learning with Unique Optimal Solutions
- Transferability of Neural Network Clinical De-identification Systems
- A Context-Enhanced De-identification System
- Label Leakage and Protection in Two-party Split Learning