paper-with-me

홈 › Papers

Having Second Thoughts? Let's hear it

2023-11-26 · Jung H. Lee, Sujith Vijayan

Deep learning models loosely mimic bottom-up signal pathways from low-order sensory areas to high-order cognitive areas. After training, DL models can outperform humans on some domain-specific tasks, but their decision-making process has been known to be easily disrupted. Since the human brain consists of multiple functional areas highly connected to one another and relies on intricate interplays between bottom-up and top-down (from high-order to low-order areas) processing, we hypothesize that incorporating top-down signal processing may make DL models more robust. To address this hypothesis, we propose a certification process mimicking selective attention and test if it could make DL models more robust. Our empirical evaluations suggest that this newly proposed certification can improve DL models' accuracy and help us build safety measures to alleviate their vulnerabilities with both artificial and natural adversarial examples.

📄 PDF Abstract BibTeX arXiv:2311.15356

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Encore: Conditioning Trajectory Forecasting via Biased Ego Rehearsals

2026-05-12 · Conghao Wong, Ziqian Zou, Xinge You arxiv

Learning and representing the subjectivities of agents has become a challenging but crucial problem in the trajectory prediction task. Such subjectivities not only present specific spatial or temporal structures, but als…

Trajectory ForecastingTrajectory Prediction

Thoughts on the potential to compensate a hearing loss in noise

2021-02-24 · Marc René Schädler

The effect of hearing impairment on speech perception was described by Plomp (1978) as a sum of a loss of class A, due to signal attenuation, and a loss of class D, due to signal distortion. While a loss of class A can b…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions

2026-05-19 · Chuanyang Jin, Binze Li, Haopeng Xie, Cathy Mengying Fang 외 arxiv

Conversational AI has now reached billions of users, yet existing datasets capture only what people say, not what they think. We introduce ThoughtTrace, the first large-scale dataset that pairs real-world multi-turn huma…

Pseudo Rehearsal using non photo-realistic images

2020-04-28 · Bhasker Sri Harsha Suri, Kalidas Yeturu

Deep Neural networks forget previously learnt tasks when they are faced with learning new tasks. This is called catastrophic forgetting. Rehearsing the neural network with the training data of the previous task can prote…

image-classificationImage Classification

A Novel Transfer Learning-Based Approach for Screening Pre-existing Heart Diseases Using Synchronized ECG Signals and Heart Sounds

2021-02-02 · Ramith Hettiarachchi, Udith Haputhanthri, Kithmini Herath, Hasindu Kariyawasam 외

Diagnosing pre-existing heart diseases early in life is important as it helps prevent complications such as pulmonary hypertension, heart rhythm problems, blood clots, heart failure and sudden cardiac arrest. To identify…

RhythmTransfer Learning