Zobrazeno 1 - 10
of 316
pro vyhledávání: '"Barner, Kenneth"'
Autor:
Bayram, Samet, Barner, Kenneth
This paper presents GReAT (Graph Regularized Adversarial Training), a novel regularization method designed to enhance the robust classification performance of deep learning models. Adversarial examples, characterized by subtle perturbations that can
Externí odkaz:
http://arxiv.org/abs/2310.05336
Autor:
Li, Jicheng, Chheang, Vuthea, Kullu, Pinar, Brignac, Eli, Guo, Zhang, Barner, Kenneth E., Bhat, Anjana, Barmaki, Roghayeh Leila
Autism spectrum disorder (ASD) is a developmental disorder characterized by significant social communication impairments and difficulties perceiving and presenting communication cues. Machine learning techniques have been broadly adopted to facilitat
Externí odkaz:
http://arxiv.org/abs/2306.08243
Autor:
Guo, Zhang, Chheang, Vuthea, Li, Jicheng, Barner, Kenneth E., Bhat, Anjana, Barmaki, Roghayeh
Social visual behavior, as a type of non-verbal communication, plays a central role in studying social cognitive processes in interactive and complex settings of autism therapy interventions. However, for social visual behavior analytics in children
Externí odkaz:
http://arxiv.org/abs/2302.08293
Autor:
Bayram, Samet, Barner, Kenneth
Adversarial machine learning is an emerging area showing the vulnerability of deep learning models. Exploring attack methods to challenge state of the art artificial intelligence (A.I.) models is an area of critical concern. The reliability and robus
Externí odkaz:
http://arxiv.org/abs/2208.14302
Autor:
Lan, Xinjie, Barner, Kenneth
Recently, Mutual Information (MI) has attracted attention in bounding the generalization error of Deep Neural Networks (DNNs). However, it is intractable to accurately estimate the MI in DNNs, thus most previous works have to relax the MI bound, whic
Externí odkaz:
http://arxiv.org/abs/2106.10262
Autor:
Lan, Xinjie, Barner, Kenneth E.
In this paper, we propose a probabilistic representation of MultiLayer Perceptrons (MLPs) to improve the information-theoretic interpretability. Above all, we demonstrate that the activations being i.i.d. is not valid for all the hidden layers of MLP
Externí odkaz:
http://arxiv.org/abs/2010.14054
We study PAC-Bayesian generalization bounds for Multilayer Perceptrons (MLPs) with the cross entropy loss. Above all, we introduce probabilistic explanations for MLPs in two aspects: (i) MLPs formulate a family of Gibbs distributions, and (ii) minimi
Externí odkaz:
http://arxiv.org/abs/2006.08888
This paper presents an audiovisual-based emotion recognition hybrid network. While most of the previous work focuses either on using deep models or hand-engineered features extracted from images, we explore multiple deep models built on both images a
Externí odkaz:
http://arxiv.org/abs/2002.09023
Autor:
Lan, Xinjie, Barner, Kenneth E.
Generalization is essential for deep learning. In contrast to previous works claiming that Deep Neural Networks (DNNs) have an implicit regularization implemented by the stochastic gradient descent, we demonstrate explicitly Bayesian regularizations
Externí odkaz:
http://arxiv.org/abs/1910.09732