Beyond mimicking under-represented emotions: deep data augmentation with emotional subspace constraints for EEG-based emotion recognition

Z Zhang, S Zhong, Y Liu - Proceedings of the AAAI conference on …, 2024‏ - ojs.aaai.org
In recent years, using Electroencephalography (EEG) to recognize emotions has garnered
considerable attention. Despite advancements, limited EEG data restricts its potential. Thus …

In defense of core-set: A density-aware core-set selection for active learning

Y Kim, B Shin - Proceedings of the 28th ACM SIGKDD conference on …, 2022‏ - dl.acm.org
Active learning enables the efficient construction of a labeled dataset by labeling informative
samples from an unlabeled dataset. In a real-world active learning scenario, the use of …

AIMEE: An Exploratory Study of How Rules Support AI Developers to Explain and Edit Models

D Piorkowski, I Vejsbjerg, O Cornec, EM Daly… - Proceedings of the …, 2023‏ - dl.acm.org
In real-world applications when deploying Machine Learning (ML) models, initial model
development includes close analysis of the model results and behavior by a data scientist …

Understanding deep learning via decision boundary

S Lei, F He, Y Yuan, D Tao - IEEE Transactions on Neural …, 2023‏ - ieeexplore.ieee.org
This article discovers that the neural network (NN) with lower decision boundary (DB)
variability has better generalizability. Two new notions, algorithm DB variability and-data DB …

Artificial Intelligence‐Assisted Decision‐Making Method for Legal Judgment Based on Deep Neural Network

W Ma - Mobile Information Systems, 2022‏ - Wiley Online Library
With the arrival of the third revolution of artificial intelligence, the applications of artificial
intelligence in the fields of automatic driving, image recognition, smart home, machine …

PICE: Polyhedral Complex Informed Counterfactual Explanations

MJ Villani, E Albini, S Sharma, S Mishra… - Proceedings of the …, 2024‏ - ojs.aaai.org
Polyhedral geometry can be used to shed light on the behaviour of piecewise linear neural
networks, such as ReLU-based architectures. Counterfactual explanations are a popular …

Linking in Style: Understanding learned features in deep learning models

MH Wehrheim, P Osuna-Vargas… - European Conference on …, 2024‏ - Springer
Convolutional neural networks (CNNs) learn abstract features to perform object
classification, but understanding these features remains challenging due to difficult-to …

Optimizing few-shot learning based on variational autoencoders

R Wei, A Mahmood - Entropy, 2021‏ - mdpi.com
Despite the importance of few-shot learning, the lack of labeled training data in the real
world makes it extremely challenging for existing machine learning methods because this …

Human-in-the-loop model explanation via verbatim boundary identification in generated neighborhoods

X Zeng, F Song, Z Li, K Chusap, C Liu - … Extraction: 5th IFIP TC 5, TC 12 …, 2021‏ - Springer
The black-box nature of machine learning models limits their use in case-critical
applications, raising faithful and ethical concerns that lead to trust crises. One possible way …

Dataset Ownership Verification in Contrastive Pre-trained Models

Y **e, J Song, M Xue, H Zhang, X Wang, B Hu… - arxiv preprint arxiv …, 2025‏ - arxiv.org
High-quality open-source datasets, which necessitate substantial efforts for curation, has
become the primary catalyst for the swift progress of deep learning. Concurrently, protecting …