no code implementations • 1 May 2024 • Shikhar Tuli, Chi-Heng Lin, Yen-Chang Hsu, Niraj K. Jha, Yilin Shen, Hongxia Jin
We also propose systematic qualitative and quantitative methods to rigorously test the quality of generated text for non-autoregressive generation.
no code implementations • 13 Mar 2024 • Chia-Hao Li, Niraj K. Jha
When adapting to a new domain, it exploits real data from the new distribution and the current model to generate synthetic data that retain the learned knowledge of previous domains.
no code implementations • 2 Feb 2024 • Bhishma Dedhia, Niraj K. Jha
Finally, we formulate the NSI program generator model to use the dense associations inferred from the alignment model to generate object-centric programs from slots.
no code implementations • 16 Aug 2023 • Shikhar Tuli, Niraj K. Jha
In graph-based search, BREATHE outperforms the next-best baseline, i. e., a graphical version of Gaussian-process-based Bayesian optimization, with up to 64. 9% higher performance.
no code implementations • 27 May 2023 • Hongjie Wang, Bhishma Dedhia, Niraj K. Jha
Deployment of Transformer models on edge devices is becoming increasingly challenging due to the exponentially growing inference cost that scales quadratically with the number of tokens in the input sequence.
no code implementations • 9 May 2023 • Chia-Hao Li, Niraj K. Jha
We demonstrate DOCTOR's efficacy in maintaining high disease classification accuracy with a single DNN model in various CL experiments.
no code implementations • 8 May 2023 • Sayeri Lala, Niraj K. Jha
The randomized controlled trial (RCT) is the gold standard for estimating the average treatment effect (ATE) of a medical intervention but requires 100s-1000s of subjects, making it expensive and difficult to implement.
no code implementations • 27 Mar 2023 • Shikhar Tuli, Niraj K. Jha
To effectively execute this method on hardware for a diverse set of transformer architectures, we propose ELECTOR, a framework that simulates transformer inference and training on a design space of accelerators.
no code implementations • 24 Mar 2023 • Shikhar Tuli, Niraj K. Jha
In this work, we propose a framework, called ProTran, to profile the hardware performance measures for a design space of transformer architectures and a diverse set of edge devices.
1 code implementation • 28 Feb 2023 • Shikhar Tuli, Niraj K. Jha
On the other hand, AccelTran-Server achieves 5. 73$\times$ higher throughput and 3. 69$\times$ lower energy consumption compared to the state-of-the-art transformer co-processor, Energon.
2 code implementations • 7 Dec 2022 • Shikhar Tuli, Chia-Hao Li, Ritvik Sharma, Niraj K. Jha
AccelBench performs cycle-accurate simulations for a diverse set of accelerator architectures in a vast design space.
1 code implementation • 17 Aug 2022 • Chang Yue, Niraj K. Jha
We propose a novel framework, called CTRL (Clustering TRaining Losses for label error detection), to detect label errors in multi-class datasets.
no code implementations • 9 Jul 2022 • Bhishma Dedhia, Roshini Balasubramanian, Niraj K. Jha
The Synthetic Control method has pioneered a class of powerful data-driven techniques to estimate the counterfactual reality of a unit from donor units.
no code implementations • 23 May 2022 • Shikhar Tuli, Bhishma Dedhia, Shreshth Tuli, Niraj K. Jha
We also propose a novel NAS policy, called BOSHNAS, that leverages this new scheme, Bayesian modeling, and second-order optimization, to quickly train and use a neural surrogate model to converge to the optimal architecture.
no code implementations • 7 Aug 2021 • Tanujay Saha, Najwa Aaraj, Niraj K. Jha
The core network architecture of telecommunication systems has undergone a paradigm shift in the fifth-generation (5G)networks.
no code implementations • 31 May 2021 • Jacob Brown, Tanujay Saha, Niraj K. Jha
Internet-of-Things (IoT) and cyber-physical systems (CPSs) may consist of thousands of devices connected in a complex network topology.
no code implementations • 5 Apr 2021 • Prerit Terway, Kenza Hamidouche, Niraj K. Jha
In the second step, we use an inverse design to search over a continuous space and fine-tune the component values with the goal of improving the value of the objective function.
no code implementations • 5 Apr 2021 • Sanjai Narain, Emily Mak, Dana Chee, Brendan Englot, Kishore Pochiraju, Niraj K. Jha, Karthik Narayan
This paper presents a new method of solving the inverse design problem namely, given requirements or constraints on output, find an input that also optimizes an objective function.
no code implementations • 20 Feb 2021 • Shayan Hassantabar, Joe Zhang, Hongxu Yin, Niraj K. Jha
At the patient level, MHDeep DNNs achieve an accuracy of 100%, 100%, and 90. 0% for the three mental health disorders, respectively.
no code implementations • 7 Jan 2021 • Tanujay Saha, Najwa Aaraj, Neel Ajjarapu, Niraj K. Jha
The novelty of this approach lies in extracting intelligence from known real-world CPS/IoT attacks, representing them in the form of regular expressions, and employing machine learning (ML) techniques on this ensemble of regular expressions to generate new attack vectors and security vulnerabilities.
no code implementations • 19 Oct 2020 • Sanjai Narain, Emily Mak, Dana Chee, Todd Huster, Jeremy Cohen, Kishore Pochiraju, Brendan Englot, Niraj K. Jha, Karthik Narayan
Central to the design of many robot systems and their controllers is solving a constrained blackbox optimization problem.
no code implementations • 12 Oct 2020 • Shayan Hassantabar, Prerit Terway, Niraj K. Jha
The synthetic data generation module targets both the categorical and continuous features.
no code implementations • 21 Sep 2020 • Prerit Terway, Kenza Hamidouche, Niraj K. Jha
In the second step, we use an inverse design to search over a continuous space to fine-tune the component values and meet the diverse set of system requirements.
no code implementations • 29 Jul 2020 • Wenhan Xia, Hongxu Yin, Xiaoliang Dai, Niraj K. Jha
Modern deep neural networks are powerful and widely applicable models that extract task-relevant information through multi-level abstraction.
no code implementations • 20 Jul 2020 • Shayan Hassantabar, Novati Stefano, Vishweshwar Ghanakota, Alessandra Ferrari, Gregory N. Nicola, Raffaele Bruno, Ignazio R. Marino, Kenza Hamidouche, Niraj K. Jha
The novel coronavirus (SARS-CoV-2) has led to a pandemic.
no code implementations • 18 Apr 2020 • Wenhan Xia, Hongxu Yin, Niraj K. Jha
These large, deep models are often unsuitable for real-world applications, due to their massive computational cost, high memory bandwidth, and long latency.
2 code implementations • CVPR 2020 • Hongxu Yin, Pavlo Molchanov, Zhizhong Li, Jose M. Alvarez, Arun Mallya, Derek Hoiem, Niraj K. Jha, Jan Kautz
We introduce DeepInversion, a new method for synthesizing images from the image distribution used to train a deep neural network.
no code implementations • 12 Dec 2019 • Shayan Hassantabar, Xiaoliang Dai, Niraj K. Jha
On MNIST dataset, our CNN architecture achieves an error rate of 0. 66%, with 8. 6x fewer parameters compared to the LeNet-5 baseline.
no code implementations • 11 Oct 2019 • Hongxu Yin, Bilal Mukadam, Xiaoliang Dai, Niraj K. Jha
For server (edge) side inference, we achieve a 96. 3% (95. 3%) accuracy in classifying diabetics against healthy individuals, and a 95. 7% (94. 6%) accuracy in distinguishing among type-1/type-2 diabetic, and healthy individuals.
no code implementations • 2 Sep 2019 • Ye Yu, Niraj K. Jha
To take advantage of sparsity, some accelerator designs explore sparsity encoding and evaluation on CNN accelerators.
Hardware Architecture
no code implementations • 29 May 2019 • Ayten Ozge Akmandor, Jorge Ortiz, Irene Manotas, Bongjun Ko, Niraj K. Jha
SECRET performs classifications by fusing the semantic information of the labels with the available data: it combines the feature space of the supervised algorithms with the semantic space of the NLP algorithms and predicts labels based on this joint space.
no code implementations • 27 May 2019 • Xiaoliang Dai, Hongxu Yin, Niraj K. Jha
Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications.
no code implementations • 19 Apr 2019 • Shayan Hassantabar, Zeyu Wang, Niraj K. Jha
To address these challenges, we propose a two-step neural network synthesis methodology, called DR+SCANN, that combines two complementary approaches to design compact and accurate DNNs.
no code implementations • 18 Mar 2019 • Ye Yu, Yingmin Li, Shuai Che, Niraj K. Jha, Weifeng Zhang
It models the accelerator design task as a multi-dimensional optimization problem.
no code implementations • 30 Jan 2019 • Hongxu Yin, Guoyang Chen, Yingmin Li, Shuai Che, Weifeng Zhang, Niraj K. Jha
In this work, we propose a hardware-guided symbiotic training methodology for compact, accurate, yet execution-efficient inference models.
1 code implementation • CVPR 2019 • Xiaoliang Dai, Peizhao Zhang, Bichen Wu, Hongxu Yin, Fei Sun, Yanghan Wang, Marat Dukhan, Yunqing Hu, Yiming Wu, Yangqing Jia, Peter Vajda, Matt Uyttendaele, Niraj K. Jha
We formulate platform-aware NN architecture search in an optimization framework and propose a novel algorithm to search for optimal architectures aided by efficient accuracy and resource (latency and/or energy) predictors.
no code implementations • 30 May 2018 • Xiaoliang Dai, Hongxu Yin, Niraj K. Jha
To address these problems, we propose a hidden-layer LSTM (H-LSTM) that adds hidden layers to LSTM's original one level non-linear control gates.
no code implementations • 6 Nov 2017 • Xiaoliang Dai, Hongxu Yin, Niraj K. Jha
To address these problems, we introduce a network growth algorithm that complements network pruning to learn both weights and compact DNN architectures during training.