Adaptive Clustering of Robust Semantic Representations for Adversarial Image Purification

no code implementations • 5 Apr 2021 • Samuel Henrique Silva, Arun Das, Ian Scarff, Peyman Najafirad

In order to evaluate the most adequate SRD, we rely on the distance between robust latent representations and semantic cluster distributions.

Clustering Semantic Similarity +1

AI-Augmented Behavior Analysis for Children with Developmental Disabilities: Building Towards Precision Treatment

no code implementations • 21 Feb 2021 • Shadi Ghafghazi, Amarie Carnett, Leslie Neely, Arun Das, Paul Rad

However, this process overburdens ABAs by requiring the clinicians to collect and analyze data, identify the problem behaviors, conduct pattern analysis to categorize and predict categorical outcomes, hypothesize responsiveness to treatments, and detect the effects of treatment plans.

Decision Making

Stuttering Speech Disfluency Prediction using Explainable Attribution Vectors of Facial Muscle Movements

no code implementations • 2 Oct 2020 • Arun Das, Jeffrey Mock, Henry Chacon, Farzan Irani, Edward Golob, Peyman Najafirad

during speech utterance.

Blocking Explainable Artificial Intelligence (XAI)

Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey

no code implementations • 16 Jun 2020 • Arun Das, Paul Rad

Nowadays, deep neural networks are widely used in mission critical systems such as healthcare, self-driving vehicles, and military which have direct impact on human lives.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI)

Encoderless Gimbal Calibration of Dynamic Multi-Camera Clusters

no code implementations • 24 Jul 2018 • Christopher L. Choi, Jason Rebello, Leonid Koppel, Pranav Ganti, Arun Das, Steven L. Waslander

In this paper, we present an encoderless approach for DCC calibration which simultaneously estimates the kinematic parameters of the transformation chain as well as the unknown joint angles.