no code implementations • 4 Apr 2024 • Hasib-Al Rashid, Argho Sarkar, Aryya Gangopadhyay, Maryam Rahnemoonfar, Tinoosh Mohsenin
Traditional machine learning models often require powerful hardware, making them unsuitable for deployment on resource-limited devices.
no code implementations • 18 Dec 2023 • Edward Humes, Mozhgan Navardi, Tinoosh Mohsenin
This model is compressed and optimized to kilobytes of parameters in order to fit onboard such edge devices.
1 code implementation • 9 Nov 2023 • Bharat Prakash, Tim Oates, Tinoosh Mohsenin
However, using LLMs to solve real world problems is hard because they are not grounded in the current task.
no code implementations • 17 Aug 2023 • Tejaswini Manjunath, Mozhgan Navardi, Prakhar Dixit, Bharat Prakash, Tinoosh Mohsenin
In real-world environments with sparse rewards and multiple goals, learning is still a major challenge and Reinforcement Learning (RL) algorithms fail to learn good policies.
no code implementations • 2 Nov 2022 • Arnab Neelim Mazumder, Niall Lyons, Ashutosh Pandey, Avik Santra, Tinoosh Mohsenin
In this work, model explanations are fed back to the feed-forward training to help the model generalize better.
no code implementations • 16 Oct 2022 • Bharat Prakash, Nicholas Waytowich, Tim Oates, Tinoosh Mohsenin
Learning to solve long horizon temporally extended tasks with reinforcement learning has been a challenge for several years now.
no code implementations • 9 Feb 2022 • Hasib-Al Rashid, Pretom Roy Ovi, Carl Busart, Aryya Gangopadhyay, Tinoosh Mohsenin
With the emergence of Artificial Intelligence (AI), new attention has been given to implement AI algorithms on resource constrained tiny devices to expand the application domain of IoT.
no code implementations • 4 Feb 2022 • Arnab Neelim Mazumder, Tinoosh Mohsenin
We propose a regression-based network exploration technique that considers the scaling of the network filters ($s$) and quantization ($q$) of the network layers, leading to a friendly and energy-efficient configuration for FPGA hardware implementation.
no code implementations • 7 Nov 2021 • Bharat Prakash, Nicholas Waytowich, Tinoosh Mohsenin, Tim Oates
In this work, we propose a method for automatic goal generation using a dynamical distance function (DDF) in a self-supervised fashion.
no code implementations • 9 Oct 2021 • Bharat Prakash, Nicholas Waytowich, Tim Oates, Tinoosh Mohsenin
The low-level controller executes the sub-tasks based on the language commands.
no code implementations • 26 Nov 2020 • Morteza Hosseini, Haoran Ren, Hasib-Al Rashid, Arnab Neelim Mazumder, Bharat Prakash, Tinoosh Mohsenin
Pulmonary diseases impact millions of lives globally and annually.
no code implementations • 26 Jun 2020 • Ali Mirzaeian, Jana Kosecka, Houman Homayoun, Tinoosh Mohsenin, Avesta Sasan
This paper proposes an ensemble learning model that is resistant to adversarial attacks.
no code implementations • 16 Jan 2020 • Farnaz Behnia, Ali Mirzaeian, Mohammad Sabokrou, Sai Manoj, Tinoosh Mohsenin, Khaled N. Khasawneh, Liang Zhao, Houman Homayoun, Avesta Sasan
In this paper, we propose Code-Bridged Classifier (CBC), a framework for making a Convolutional Neural Network (CNNs) robust against adversarial attacks without increasing or even by decreasing the overall models' computational complexity.
no code implementations • 29 Sep 2019 • Sunil Gandhi, Tim Oates, Tinoosh Mohsenin, Nicholas Waytowich
In this paper, we present a method for learning from video demonstrations by using human feedback to construct a mapping between the standard representation of the agent and the visual representation of the demonstration.
no code implementations • 25 Mar 2019 • Bharat Prakash, Mark Horton, {Nicholas R. Waytowich, William David Hairston, Tim Oates, Tinoosh Mohsenin
This compression model is vital to efficiently learn policies, especially when learning on embedded systems.
no code implementations • 22 Mar 2019 • Bharat Prakash, Mohit Khatwani, Nicholas Waytowich, Tinoosh Mohsenin
Recent progress in AI and Reinforcement learning has shown great success in solving complex problems with high dimensional state spaces.
no code implementations • Advances in Knowledge Discovery and Data Mining. PAKDD 2018 2018 • Sunil Gandhi, Tim Oates, Tinoosh Mohsenin, David Hairston
This step is especially important if the noise in data originates from diverse sources.
no code implementations • 28 Aug 2017 • JT Turner, Adam Page, Tinoosh Mohsenin, Tim Oates
Ubiquitous bio-sensing for personalized health monitoring is slowly becoming a reality with the increasing availability of small, diverse, robust, high fidelity sensors.
no code implementations • 19 Dec 2014 • Siddharth Pramod, Adam Page, Tinoosh Mohsenin, Tim Oates
We explore the use of neural networks trained with dropout in predicting epileptic seizures from electroencephalographic data (scalp EEG).