no code implementations • 5 Apr 2024 • Zishen Wan, Che-Kai Liu, Mohamed Ibrahim, Hanchen Yang, Samuel Spetalnick, Tushar Krishna, Arijit Raychowdhury
Disentangling attributes of various sensory signals is central to human-like perception and reasoning and a critical task for higher-order cognitive and neuro-symbolic AI systems.
no code implementations • 2 Jan 2024 • Zishen Wan, Che-Kai Liu, Hanchen Yang, Chaojian Li, Haoran You, Yonggan Fu, Cheng Wan, Tushar Krishna, Yingyan Lin, Arijit Raychowdhury
The remarkable advancements in artificial intelligence (AI), primarily driven by deep neural networks, have significantly impacted various aspects of our lives.
no code implementations • 29 Jun 2023 • Kshitij Bhardwaj, Zishen Wan, Arijit Raychowdhury, Ryan Goldhahn
While deep neural networks are being utilized heavily for autonomous driving, they need to be adapted to new unseen environmental conditions for which they were not trained.
no code implementations • 22 Feb 2023 • Ashwin Bhat, Arijit Raychowdhury
Integrated Gradients (IG) is a popular XAI algorithm that attributes relevance scores to input features commensurate with their contribution to the model's output.
no code implementations • 19 Oct 2022 • Ashwin Bhat, Adou Sangbone Assoa, Arijit Raychowdhury
In this work, we first analyze the dataflow of gradient backpropagation based feature attribution algorithms to determine the resource overhead required over inference.
no code implementations • 21 Jul 2022 • Ashwin Sanjay Lele, Arijit Raychowdhury
However, the algorithms for processing the data either borrow frame like setup limiting the speed or suffer from lower accuracy.
no code implementations • 14 Mar 2022 • Zishen Wan, Aqeel Anwar, Abdulrahman Mahmoud, Tianyu Jia, Yu-Shun Hsiao, Vijay Janapa Reddi, Arijit Raychowdhury
Swarm intelligence is being increasingly deployed in autonomous systems, such as drones and unmanned vehicles.
no code implementations • 16 Sep 2021 • Adarsh Kumar Kosta, Malik Aqeel Anwar, Priyadarshini Panda, Arijit Raychowdhury, Kaushik Roy
To address this challenge, we propose a reconfigurable architecture with preemptive exits for efficient deep RL (RAPID-RL).
no code implementations • 11 Apr 2021 • Tian Gao, Zishen Wan, Yuyang Zhang, Bo Yu, Yanjun Zhang, Shaoshan Liu, Arijit Raychowdhury
Stereo matching is a critical task for robot navigation and autonomous vehicles, providing the depth estimation of surroundings.
no code implementations • 1 Apr 2021 • Zishen Wan, Yuyang Zhang, Arijit Raychowdhury, Bo Yu, Yanjun Zhang, Shaoshan Liu
In our past few years' of commercial deployment experiences, we identify localization as a critical task in autonomous machine applications, and a great acceleration target.
no code implementations • 11 Mar 2021 • Aqeel Anwar, Arijit Raychowdhury
Experimentation on different small to mid-size reinforcement learning problems show that the proposed attack method outperforms other general attack methods and the proposed modification to federated reinforcement learning algorithm was able to achieve near-optimal policies in the presence of adversarial agents.
no code implementations • 13 Sep 2020 • Zishen Wan, Bo Yu, Thomas Yuang Li, Jie Tang, Yuhao Zhu, Yu Wang, Arijit Raychowdhury, Shaoshan Liu
On the other hand, FPGA-based robotic accelerators are becoming increasingly competitive alternatives, especially in latency-critical and power-limited scenarios.
5 code implementations • 25 Aug 2020 • Aqeel Anwar, Arijit Raychowdhury
The use of these face masks has raised a serious question on the accuracy of the facial recognition system used for tracking school/office attendance and to unlock phones.
no code implementations • 8 Jun 2020 • Sihan Zeng, Aqeel Anwar, Thinh Doan, Arijit Raychowdhury, Justin Romberg
We develop a mathematical framework for solving multi-task reinforcement learning (MTRL) problems based on a type of policy gradient method.
no code implementations • 4 Jun 2020 • Brian Crafton, Samuel Spetalnick, Arijit Raychowdhury
Compute in-memory (CIM) is a promising technique that minimizes data transport, the primary performance bottleneck and energy cost of most data intensive applications.
no code implementations • 11 Apr 2020 • Justin Ting, Yan Fang, Ashwin Sanjay Lele, Arijit Raychowdhury
When humans watch their peers, visual data is processed through a visual cortex in the brain.
no code implementations • 22 Mar 2020 • Ashwin Sanjay Lele, Yan Fang, Justin Ting, Arijit Raychowdhury
However, training a legged robot to walk by learning the synchronization patterns of central pattern generators (CPG) in an SNN framework has not been shown.
no code implementations • 9 Nov 2019 • Foroozan Karimzadeh, Ningyuan Cao, Brian Crafton, Justin Romberg, Arijit Raychowdhury
Deep neural networks (DNNs) have been emerged as the state-of-the-art algorithms in broad range of applications.
1 code implementation • 12 Oct 2019 • Aqeel Anwar, Arijit Raychowdhury
Smart and agile drones are fast becoming ubiquitous at the edge of the cloud.
no code implementations • 12 Aug 2019 • Insik Yoon, Matthew Jerry, Suman Datta, Arijit Raychowdhury
In this letter, we quantify the impact of device limitations on the classification accuracy of an artificial neural network, where the synaptic weights are implemented in a Ferroelectric FET (FeFET) based in-memory processing architecture.
no code implementations • 19 Feb 2019 • Shaojie Xu, Anvesha Amaravati, Justin Romberg, Arijit Raychowdhury
We propose a novel appearance-based gesture recognition algorithm using compressed domain signal processing techniques.
1 code implementation • 30 Jan 2019 • Brian Crafton, Abhinav Parihar, Evan Gebhardt, Arijit Raychowdhury
Using a sparse feedback matrix, we show that a neuron needs only a fraction of the information previously used by the feedback alignment algorithms.
no code implementations • 22 Jul 2018 • Malik Aqeel Anwar, Arijit Raychowdhury
We present NAVREN-RL, an approach to NAVigate an unmanned aerial vehicle in an indoor Real ENvironment via end-to-end reinforcement learning RL.
no code implementations • 16 Aug 2017 • Abhinav Parihar, Matthew Jerry, Suman Datta, Arijit Raychowdhury
This motivates the current article where we demonstrate a stochastic neuron using an insulator-metal-transition (IMT) device, based on electrically induced phase-transition, in series with a tunable resistance.
no code implementations • 26 May 2016 • Anvesha A, Shaojie Xu, Ningyuan Cao, Justin Romberg, Arijit Raychowdhury
In this paper we propose an energy-efficient camera-based gesture recognition system powered by light energy for "always on" applications.