1 code implementation • 14 Feb 2024 • Xiongye Xiao, Chenyu Zhou, Heng Ping, Defu Cao, Yaxing Li, Yizhuo Zhou, Shixuan Li, Paul Bogdan
Prior studies on the emergence in large models have primarily focused on how the functional capabilities of large language models (LLMs) scale with model size.
1 code implementation • 20 Dec 2023 • Anzhe Cheng, Zhenkun Wang, Chenzhong Yin, Mingxi Cheng, Heng Ping, Xiongye Xiao, Shahin Nazarian, Paul Bogdan
This includes decisions on how to decouple network blocks and which auxiliary networks to use for each block.
no code implementations • 19 Dec 2023 • Chenzhong Yin, Hantang Zhang, Mingxi Cheng, Xiongye Xiao, Xinghe Chen, Xin Ren, Paul Bogdan
Malware represents a significant security concern in today's digital landscape, as it can destroy or disable operating systems, steal sensitive user information, and occupy valuable disk space.
no code implementations • 9 Dec 2023 • Shukai Duan, Nikos Kanakaris, Xiongye Xiao, Heng Ping, Chenyu Zhou, Nesreen K. Ahmed, Guixiang Ma, Mihai Capota, Theodore L. Willke, Shahin Nazarian, Paul Bogdan
We compare our framework with existing state-of-the-art models and show that it is more efficient with respect to speed and computational usage, as a result of the decrement in training steps and its applicability to models with fewer parameters.
no code implementations • 11 Oct 2023 • Chenzhong Yin, Mingxi Cheng, Xiongye Xiao, Xinghe Chen, Shahin Nazarian, Andrei Irimia, Paul Bogdan
Motivated by the intricacy of these collectives, we propose a neural network (NN) architecture inspired by the rules observed in nature's collective ensembles.
no code implementations • 27 Sep 2023 • Xiongye Xiao, Gengshuo Liu, Gaurav Gupta, Defu Cao, Shixuan Li, Yaxing Li, Tianqing Fang, Mingxi Cheng, Paul Bogdan
Integrating and processing information from various sources or modalities are critical for obtaining a comprehensive and accurate perception of the real world.
1 code implementation • 13 Mar 2023 • Chenzhong Yin, Mihai Udrescu, Gaurav Gupta, Mingxi Cheng, Andrei Lihu, Lucretia Udrescu, Paul Bogdan, David M Mannino, Stefan Mihaicuta
The authors show that the fractional dynamic deep learning model (FDDLM) achieves a COPD prediction accuracy of 98. 66% and can serve as a robust alternative to spirometry.
no code implementations • 12 Mar 2023 • Chenzhong Yin, Zhihong Pan, Xin Zhou, Le Kang, Paul Bogdan
While the random sampling of latent variable $z$ is useful in generating diverse photo-realistic images, it is not desirable for image rescaling when accurate restoration of the HR image is more important.
1 code implementation • 4 Mar 2023 • Xiongye Xiao, Defu Cao, Ruochen Yang, Gaurav Gupta, Gengshuo Liu, Chenzhong Yin, Radu Balan, Paul Bogdan
Coupled partial differential equations (PDEs) are key tasks in modeling the complex dynamics of many physical processes.
no code implementations • 25 Apr 2022 • Yao Xiao, Guixiang Ma, Nesreen K. Ahmed, Mihai Capota, Theodore Willke, Shahin Nazarian, Paul Bogdan
To enable heterogeneous computing systems with autonomous programming and optimization capabilities, we propose a unified, end-to-end, programmable graph representation learning (PGL) framework that is capable of mining the complexity of high-level programs down to the universal intermediate representation, extracting the specific computational patterns and predicting which code segments would run best on a specific core in heterogeneous hardware platforms.
no code implementations • 24 Apr 2022 • Mohamed Ridha Znaidi, Gaurav Gupta, Paul Bogdan
Decentralized learning is an efficient emerging paradigm for boosting the computing capability of multiple bounded computing agents.
no code implementations • 8 Nov 2021 • Mingxi Cheng, Junyao Zhang, Shahin Nazarian, Jyotirmoy Deshmukh, Paul Bogdan
Many intelligent transportation systems are multi-agent systems, i. e., both the traffic participants and the subsystems within the transportation infrastructure can be modeled as interacting agents.
no code implementations • ICLR 2022 • Gaurav Gupta, Xiongye Xiao, Radu Balan, Paul Bogdan
The Padé exponential operator uses a $\textit{recurrent structure with shared parameters}$ to model the non-linearity compared to recent neural operators that rely on using multiple linear operator layers in succession.
no code implementations • 29 Sep 2021 • Valeriu Balaban, Paul Bogdan
We prove that minimizing a weighted mean results in optimizing the higher-order moments of the loss distribution such as the variance, skewness, and kurtosis.
no code implementations • ICLR 2022 • Panagiotis Kyriakis, Jyotirmoy Deshmukh, Paul Bogdan
We present a policy gradient method for Multi-Objective Reinforcement Learning under unknown, linear preferences.
Multi-Objective Reinforcement Learning reinforcement-learning
1 code implementation • NeurIPS 2021 • Gaurav Gupta, Xiongye Xiao, Paul Bogdan
The solution of a partial differential equation can be obtained by computing the inverse operator map between the input and the solution space.
no code implementations • 29 Jul 2021 • Gaurav Gupta, Chenzhong Yin, Jyotirmoy V. Deshmukh, Paul Bogdan
Reinforcement learning (RL) is a technique to learn the control policy for an agent that interacts with a stochastic environment.
no code implementations • 28 Jul 2021 • Emily A. Reed, Guilherme Ramos, Paul Bogdan, Sérgio Pequito
First, we provide necessary and sufficient conditions for their structural state and input observability that can be efficiently verified in $O((m(n+p))^2)$, where $n$ is the number of state variables, $p$ is the number of unknown inputs, and $m$ is the number of modes.
1 code implementation • ICLR 2021 • Panagiotis Kyriakis, Iordanis Fostiropoulos, Paul Bogdan
Learning task-specific representations of persistence diagrams is an important problem in topological data analysis and machine learning.
1 code implementation • 28 Jan 2021 • Mingxi Cheng, Shahin Nazarian, Paul Bogdan
VRoC consists of a co-train engine that trains variational autoencoders (VAEs) and rumor classification components.
no code implementations • 9 Oct 2020 • Guixiang Ma, Yao Xiao, Theodore L. Willke, Nesreen K. Ahmed, Shahin Nazarian, Paul Bogdan
High-level applications, such as machine learning, are evolving from simple models based on multilayer perceptrons for simple image recognition to much deeper and more complex neural networks for self-driving vehicle control systems. The rapid increase in the consumption of memory and computational resources by these models demands the use of multi-core parallel systems to scale the execution of the complex emerging applications that depend on them.
no code implementations • 25 Sep 2019 • Mingxi Cheng, Yizhi Li, Shahin Nazarian, Paul Bogdan
However, the vigorous growth of social media contributes to the fast-spreading and far-reaching rumors.
no code implementations • ICLR 2019 • Gaurav Gupta, Mohamed Ridha Znaidi, Paul Bogdan
Extracting relevant information, causally inferring and predicting the future states with high accuracy is a crucial task for modeling complex systems.
1 code implementation • 2 Nov 2018 • Gaurav Gupta, Sergio Pequito, Paul Bogdan
Despite significant effort in understanding complex systems (CS), we lack a theory for modeling, inference, analysis and efficient control of time-varying complex networks (TVCNs) in uncertain environments.
1 code implementation • 2 Nov 2018 • Ruochen Yang, Gaurav Gupta, Paul Bogdan
Previous research of neuron activity analysis is mainly limited with effects from the spiking history of target neuron and the interaction with other neurons in the system while ignoring the influence of unknown stimuli.
no code implementations • 17 Jun 2018 • Gaurav Gupta, Sergio Pequito, Paul Bogdan
Nonetheless, often we leverage the greedy algorithms used in submodular functions to determine a solution to the non-submodular functions.
1 code implementation • 10 Mar 2018 • Gaurav Gupta, Sergio Pequito, Paul Bogdan
This paper focuses on analysis and design of time-varying complex networks having fractional order dynamics.