HypperSteer: Hypothetical Steering and Data Perturbation in Sequence Prediction with Deep Learning
Deep Recurrent Neural Networks (RNN) continues to find success in predictive decision-making with temporal event sequences. Recent studies have shown the importance and practicality of visual analytics in interpreting deep learning models for real-world applications. However, very limited work enables interactions with deep learning models and guides practitioners to form hypotheticals towards the desired prediction outcomes, especially for sequence prediction. Specifically, no existing work has addressed the what-if analysis and value perturbation along different time-steps for sequence outcome prediction. We present a model-agnostic visual analytics tool, HypperSteer, that steers hypothetical testing and allows users to perturb data for sequence predictions interactively. We showcase how HypperSteer helps in steering patient data to achieve desired treatment outcomes and discuss how HypperSteer can serve as a comprehensive solution for other practical scenarios.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingDeep LearningPredictionSimilar Papers 제목 키워드 기반
A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models
Activation steering via sparse autoencoders (SAEs) enables behavioral control of large language models without task-specific fine-tuning, but standard methods apply the steering signal at every generated token, incurring…
Towards Increasing the Robustness of Predictive Steering-Control Autonomous Navigation Systems Against Dash Cam Image Angle Perturbations Due to Pothole Encounters
Vehicle manufacturers are racing to create autonomous navigation and steering control algorithms for their vehicles. These software are made to handle various real-life scenarios such as obstacle avoidance and lane maneu…
Autonomous NavigationSteering ControlFoveation-based Mechanisms Alleviate Adversarial Examples
We show that adversarial examples, i.e., the visually imperceptible perturbations that result in Convolutional Neural Networks (CNNs) fail, can be alleviated with a mechanism based on foveations---applying the CNN in dif…
FoveationTranslationControlled Steering-Based State Preparation for Adversarial-Robust Quantum Machine Learning
Quantum machine learning (QML) provides a promising framework for leveraging quantum-mechanical effects in learning tasks. However, its vulnerability to adversarial perturbations remains a major challenge for practical d…
Quantum Machine LearningDo What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification
Reasoning Vision Language Action (VLA) models improve robotic instruction-following by generating step-by-step textual plans before low-level actions, an approach inspired by Chain-of-Thought (CoT) reasoning in language …