VR enables professionals to develop deep learning models by moving virtual objects.
problem Challenges in understanding and developing deep learning models.
method Built a VR-based DL development environment where users interact with tangible objects to construct neural networks.
result Users can develop and understand DL models intuitively through VR, with real-time accuracy feedback.
The Open University studies student online behavior in virtual learning environments.
problem Improving retention rates in online modules.
method GUHA and Markov chain-based analysis of student activity.
result Both methods are valid for modeling student activities.
PackIt creates a virtual space for testing geometric planning skills.
problem Evaluating geometric planning abilities in virtual environments.
method Developed a virtual environment, PackIt, for geometric planning tasks.
result Demonstrated the effectiveness of various methods for geometric planning.
The paper improves HER by prioritizing virtual goals and removing misleading samples.
problem Sparse reward functions in reinforcement learning.
method Prioritizing virtual goals based on instructiveness and removing misleading samples.
result Significant improvement in success rate and sample efficiency.
Enhances graph neural networks by creating virtual data examples.
problem Lack of examples to identify optimal graph rationales in graph applications.
method Introduces environment replacement to create virtual data examples and proposes a framework for rationale-environment separation and representation learning.
result Demonstrates the effectiveness and efficiency of the augmentation-based graph rationalization framework on molecular and polymer datasets.
Paper proposes a semi-supervised method for detecting concept drift in streaming environments.
problem Detecting concept drift in streaming environments with limited labeled data.
method Utilizes density estimation of posterior probabilities in partially labeled streaming data.
result Demonstrates superior concept drift detection in streaming environments with limited labeled data.
CEA augments reinforcement learning by generating counterfactual experiences.
problem Challenges in reinforcement learning, especially out-of-distribution and inefficient exploration.
method CEA uses variational autoencoders to model state transitions and introduces randomness for non-stationarity. It expands learning data through counterfactual inference.
result CEA outperforms SOTA algorithms in diverse environments.
Improves reinforcement learning for complex tasks with sparse feedback.
problem Learning optimal policies from sparse feedback is challenging.
method Three algorithms based on Hindsight Experience Replay (HER) to improve performances.
result Vast improvement in final success rate and sample efficiency.
Robots navigate wilderness trails using virtual-to-real-world transfer learning.
problem Autonomous navigation of outdoor trails is challenging due to lack of annotated training data.
method Virtual-to-real-world transfer learning with deep learning models trained on synthetic data.
result Classification accuracies of up to 95% on synthetic data and feasibility in real-world trails.
Paper introduces IAD for detecting anomalous VMMs in cloud without VMM access.
problem Anomalous VMMs in cloud-based environments without direct access.
method IAD: Indirect Anomalous VMMs Detection algorithm using VM resource utilization data.
result IAD algorithm outperforms other methods with an average F1-score of 83.7%.
Google Research Football: A new 3D physics-based game for reinforcement learning.
problem Training reinforcement learning algorithms in complex, realistic environments.
method Developed a new 3D physics-based football simulator environment.
result Reported baseline results for various reinforcement algorithms.
A machine learning environment for detecting autonomous vehicle corner cases.
problem Testing autonomous driving software in the real world is difficult.
method Connecting CARLA simulation software to TensorFlow and custom AI client software.
result The system can identify situations where AI software fails to understand the scenario.
A framework for prototype-based classifiers in changing data environments.
problem Learning in non-stationary environments with concept drift.
method Analytical methods from statistical physics applied to LVQ systems.
result Basic LVQ algorithms are suitable for non-stationary environments, but weight decay does not improve performance.
This study uses cloud telemetry to detect DoS attacks with machine learning.
problem Detecting DoS attacks in cloud environments is challenging.
method Use of machine learning algorithms on cloud telemetry data.
result k-Nearest Neighbors (kNN) and decision tree (CART) accurately identify DoS attacks.
Optimizes resource allocation for virtualized network functions based on performance profiles.
problem Mapping SLA performance requirements to dynamic virtualized infrastructure resources.
method Profile-based resource allocation using VNF performance datasets and machine learning models.
result A method to predict and recommend optimal resource allocation for network services.
Study uses sentiment analysis to predict cryptocurrency token returns in virtual reality.
problem Predicting cryptocurrency token returns in virtual reality economies.
method Used BERT for sentiment analysis and developed LSTM models integrating multi-modal features.
result Multi-modal model significantly outperforms price-only baseline in prediction accuracy.
Efficiently learn and adapt to multiple tasks with limited samples.
problem Efficiently learn and adapt to multiple tasks with limited samples.
method Learn a dynamical model during training and use it for sample-efficient adaptation at test time.
result Significantly fewer samples required for adaptation to new tasks.
Reinforcement Learning AI commonly uses reward/penalty signals that are objective and explicit in an environment -- e.g. game score, completion time, etc. -- in order to learn the optimal strategy for task performance. However, Human-AI interaction for such AI agents should include additional reinforcement that is impl…
Predicting movement of objects while the action of learning agent interacts with the dynamics of the scene still remains a key challenge in robotics. We propose a multi-layer Long Short Term Memory (LSTM) autoendocer network that predicts future frames for a robot navigating in a dynamic environment with moving obstacl…
Interactive machine learning improves deep RL in Minecraft by giving action advice.
problem Training deep RL agents in high-aliasing environments like Minecraft is computationally expensive.
method Conducted experiments with two RL algorithms, Feedback Arbitration, and Newtonian Action Advice, to give action advice to human teachers.
result Action advice from human teachers can improve agent performance in high-aliasing environments.
DyFEn simulates blockchain for fee setting in payment channels.
problem Dynamic fee setting in off-chain payment channels.
method Agent-based reinforcement learning in a blockchain simulation.
result Empirical results of reinforcement learning methods on dynamic fee setting.
Algorithm integrates uncertainty for lifelong learning in dynamic environments.
problem Continuous, lifelong learning for intelligent agents in changing conditions.
method Inspired by neuromodulatory mechanisms, integrates uncertainty for self-supervised and one-shot learning.
result Stable learning without catastrophic forgetting in a virtual environment.
GANs improve building performance model accuracy by integrating occupant behaviors.
problem Discrepancies between design and operation performance in buildings.
method Generative Adversarial Networks (GANs) to learn mixture models combining existing BPMs with occupant behaviors.
result Augmented BPMs significantly outperform existing BPMs in achieving specified performance targets.
Paper proposes a hierarchical approach to malware detection in cloud environments.
problem Malware threat in cloud computing environments.
method Machine learning on graphs, hypergraphs, and natural language for malware detection and analysis.
result Federated learning for malware detection in multicloud environments.
Improved reinforcement learning for robotics with active uncertainty reduction.
problem Infeasibility of model-free reinforcement learning methods in robotics due to safety and time constraints.
method Active uncertainty reduction-based virtual environments with adaptive sampling for metric self-improvement.
result Better modeling capacity for complex system dynamics compared to established methods.
Deep learning framework detects emotions from EEG data.
problem Detecting emotions from EEG signals.
method Temporal and spatial convolutional layers learn discriminative representations.
result TSception achieves 86.03% classification accuracy, significantly outperforming other methods.
We develop the first basic Operational Risk perspective on key risk management issues associated with the development of new forms of electronic currency in the real economy. In particular, we focus on understanding the development of new risks types and the evolution of current risk types as new components of financia…
New method identifies causal variables from multi-node interventions, expanding on previous single-node approaches.
problem Inferring high-level causal variables from low-level observations under multiple interventions.
method Exploits variance trace of ground truth causal variables and regularizes for sparsity.
result First identifiability result for causal representation learning with multiple node interventions.
Neuro-symbolic traders suppress market prices, highlighting risks to stability.
problem Understanding and quantifying the influence of AI-generated financial models on markets.
method Developed virtual neuro-symbolic traders using deep generative models and tested them in a virtual market.
result Neuro-symbolic traders suppress market prices compared to historical data, indicating potential market instability.
Efficiently updates beliefs with virtual observations.
problem Incremental belief updates in Bayesian models.
method Constructs weighted virtual observations to match posterior.
result Reconstructed posterior matches original posterior closely.
The paper proposes a method to transfer knowledge across different settings using causal theory.
problem Learning transfer across similar but different settings.
method Bayesian perspective of causal theory induction, integrating instance-level associative learning and abstract-level structural causal knowledge.
result The proposed model achieved transfer behavior across trials and learning situations, unlike RL algorithms.
Unified deep learning framework improves SV in noisy, reverberant, and long non-speech segments.
problem Robust speaker verification in adverse environments, especially short speech segments.
method Feature Pyramid Module (FPM)-based Multi-scale Aggregation (MSA), Self-adaptive Soft VAD (SAS-VAD), Masking-based Speech Enhancement (SE).
result The proposed method outperforms baseline systems in challenging conditions.
We introduce a new virtual environment for simulating a card game known as "Big 2". This is a four-player game of imperfect information with a relatively complicated action space (being allowed to play 1,2,3,4 or 5 card combinations from an initial starting hand of 13 cards). As such it poses a challenge for many curre…
Self-Predictive Representations improves data-efficient reinforcement learning from limited interaction.
problem Efficient reinforcement learning from limited data.
method Train agents to predict future latent state representations using self-supervised objectives.
result Achieves a median human-normalized score of 0.415 on Atari with 100k steps of interaction, 55% improvement over previous state-of-the-art.
Paper develops a model-based RL framework for portfolio optimization in financial markets.
problem Complex, non-Gaussian environment dynamics in financial markets.
method Heavy-tailed preserving normalizing flows for environment simulation; model-based reinforcement learning framework.
result Proposed method outperforms in various financial markets, especially during the pandemic.
A deep model learns to infer fluorescence labels from unlabeled microscopy images.
problem Challenges in obtaining high quality images of cellular structures due to complex environments and label staining limitations.
method Developed a novel deep model using global pixel transformer layers and dense blocks, incorporating multi-scale input strategy.
result Significantly outperforms state-of-the-art methods in fluorescence image prediction tasks.
Q2-Opt improves robot grasping success and efficiency.
problem Improving robot grasping success and efficiency in vision-based tasks.
method Quantile QT-Opt, a distributional variant of Q-learning for continuous domains.
result Q2-Opt achieves superior grasping success and is more sample efficient.
In a typical online learning scenario, a learner is required to process a large data stream using a small memory buffer. Such a requirement is usually in conflict with a learner's primary pursuit of prediction accuracy. To address this dilemma, we introduce a novel Bayesian online classi cation algorithm, called the Vi…
Safe reinforcement learning framework using optimal transport for robustness.
problem Robustness and safety in deep reinforcement learning with limited data assumptions.
method Optimal transport perturbations to construct worst-case virtual state transitions.
result Significantly improved safety at deployment time compared to standard methods.
This paper improves route choice models by incorporating contextual factors.
problem Existing route choice models lack consideration of dynamic contextual conditions.
method Knowledge distillation from Stated Choice Experiments in Immersive Virtual Environment.
result High-fidelity route choice models with increased predictive power.
Study uses GPLFM to create Digital Twin for ferry quay health monitoring.
problem Deterioration of ferry quays due to harsh maritime environments and impacts.
method Gaussian Process Latent Force Model (GPLFM) integrating physics-based model and machine learning.
result GPLFM provides accurate acceleration response estimates, even under simplifying assumptions.
We propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the conditional label distribution given input. Virtual adversarial loss is defined as the robustness of the conditional label distribution around each input data point against local perturbation. Unlike adver…
The paper calculates bridge numbers for knots using machine learning.
problem Determining the bridge number for virtual knots with multiple definitions.
method Employed computational techniques and machine learning models to classify knots based on their bridge numbers.
result Demonstrated that the bridge number for virtual knots can differ significantly.
Modern computer vision algorithms typically require expensive data acquisition and accurate manual labeling. In this work, we instead leverage the recent progress in computer graphics to generate fully labeled, dynamic, and photo-realistic proxy virtual worlds. We propose an efficient real-to-virtual world cloning meth…
Animals execute goal-directed behaviours despite the limited range and scope of their sensors. To cope, they explore environments and store memories maintaining estimates of important information that is not presently available. Recently, progress has been made with artificial intelligence (AI) agents that learn to per…
KANEL combines models for early hit enrichment in virtual screening.
problem Assessing model accuracy in chemical bioactivity predictions.
method Ensemble workflow using Kolmogorov-Arnold Networks (KANs) and other models.
result Improves early hit enrichment metrics like PPV@N.
New virtualized Δ-move simplifies virtual knots and links.
problem Simplifying virtual knots and links.
method Introducing a new local deformation called the virtualized Δ-move.
result Virtualized Δ-move is an unknotting operation for virtual knots.
Virtual index cocycles reformulate virtual link invariants.
problem No specific problem stated; focuses on reformulation.
method Using virtual index cocycles to reformulate invariants.
result Unified reformulation of virtual link invariants.