Search Results for author: Amir Emad Marvasti

Found 6 papers, 0 papers with code

Out of Distribution Detection, Generalization, and Robustness Triangle with Maximum Probability Theorem

no code implementations23 Mar 2022 Amir Emad Marvasti, Ehsan Emad Marvasti, Ulas Bagci

Maximum Probability Framework, powered by Maximum Probability Theorem, is a recent theoretical development in artificial intelligence, aiming to formally define probabilistic models, guiding development of objective functions, and regularization of probabilistic models.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Feature Sharing and Integration for Cooperative Cognition and Perception with Volumetric Sensors

no code implementations16 Nov 2020 Ehsan Emad Marvasti, Arash Raftari, Amir Emad Marvasti, Yaser P. Fallah, Rui Guo, HongSheng Lu

In this paper, we examine the requirements, limitations, and performance of different cooperative perception techniques, and present an in-depth analysis of the notion of Deep Feature Sharing (DFS).

object-detection Object Detection

Bandwidth-Adaptive Feature Sharing for Cooperative LIDAR Object Detection

no code implementations22 Oct 2020 Ehsan Emad Marvasti, Arash Raftari, Amir Emad Marvasti, Yaser P. Fallah

In this work, we propose a mechanism to add flexibility in adapting to communication channel capacity and a novel decentralized shared data alignment method to further improve cooperative object detection performance.

Autonomous Vehicles Object +2

Cooperative LIDAR Object Detection via Feature Sharing in Deep Networks

no code implementations19 Feb 2020 Ehsan Emad Marvasti, Arash Raftari, Amir Emad Marvasti, Yaser P. Fallah, Rui Guo, HongSheng Lu

The recent advancements in communication and computational systems has led to significant improvement of situational awareness in connected and autonomous vehicles.

Autonomous Vehicles object-detection +1

Maximum Probability Theorem: A Framework for Probabilistic Learning

no code implementations21 Oct 2019 Amir Emad Marvasti, Ehsan Emad Marvasti, Ulas Bagci, Hassan Foroosh

Instead, the regularizing effects of assuming prior over parameters is seen through maximizing probabilities of models or according to information theory, minimizing the information content of a model.

Rediscovering Deep Neural Networks Through Finite-State Distributions

no code implementations26 Sep 2018 Amir Emad Marvasti, Ehsan Emad Marvasti, George Atia, Hassan Foroosh

We propose a new way of thinking about deep neural networks, in which the linear and non-linear components of the network are naturally derived and justified in terms of principles in probability theory.

Cannot find the paper you are looking for? You can Submit a new open access paper.