Search Results for author:
Found 37 papers, 5 papers with code
PAGE: Domain-Incremental Adaptation with Past-Agnostic Generative Replay for Smart Healthcare
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.
Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations
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.
BREATHE: Second-Order Gradients and Heteroscedastic Emulation based Design Space Exploration
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.
Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers
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.
DOCTOR: A Multi-Disease Detection Continual Learning Framework Based on Wearable Medical Sensors
We demonstrate DOCTOR's efficacy in maintaining high disease classification accuracy with a single DNN model in various CL experiments.
SECRETS: Subject-Efficient Clinical Randomized Controlled Trials using Synthetic Intervention
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.
TransCODE: Co-design of Transformers and Accelerators for Efficient Training and Inference
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.
EdgeTran: Co-designing Transformers for Efficient Inference on Mobile Edge Platforms
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.
AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers
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.
CODEBench: A Neural Architecture and Hardware Accelerator Co-Design Framework
AccelBench performs cycle-accurate simulations for a diverse set of accelerator architectures in a vast design space.
CTRL: Clustering Training Losses for Label Error Detection
We propose a novel framework, called CTRL (Clustering TRaining Losses for label error detection), to detect label errors in multi-class datasets.
SCouT: Synthetic Counterfactuals via Spatiotemporal Transformers for Actionable Healthcare
The Synthetic Control method has pioneered a class of powerful data-driven techniques to estimate the counterfactual reality of a unit from donor units.
FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?
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.
Machine Learning Assisted Security Analysis of 5G-Network-Connected Systems
The core network architecture of telecommunication systems has undergone a paradigm shift in the fifth-generation (5G)networks.
GRAVITAS: Graphical Reticulated Attack Vectors for Internet-of-Things Aggregate Security
Internet-of-Things (IoT) and cyber-physical systems (CPSs) may consist of thousands of devices connected in a complex network topology.
Fast Design Space Exploration of Nonlinear Systems: Part I
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.
Fast Design Space Exploration of Nonlinear Systems: Part II
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.
MHDeep: Mental Health Disorder Detection System based on Body-Area and Deep Neural Networks
At the patient level, MHDeep DNNs achieve an accuracy of 100%, 100%, and 90. 0% for the three mental health disorders, respectively.
SHARKS: Smart Hacking Approaches for RisK Scanning in Internet-of-Things and Cyber-Physical Systems based on Machine Learning
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.
Robot Design With Neural Networks, MILP Solvers and Active Learning
Central to the design of many robot systems and their controllers is solving a constrained blackbox optimization problem.
TUTOR: Training Neural Networks Using Decision Rules as Model Priors
The synthetic data generation module targets both the categorical and continuous features.
DISPATCH: Design Space Exploration of Cyber-Physical Systems
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.
Fully Dynamic Inference with Deep Neural Networks
Modern deep neural networks are powerful and widely applicable models that extract task-relevant information through multi-level abstraction.
CovidDeep: SARS-CoV-2/COVID-19 Test Based on Wearable Medical Sensors and Efficient Neural Networks
The novel coronavirus (SARS-CoV-2) has led to a pandemic.
Efficient Synthesis of Compact Deep Neural Networks
These large, deep models are often unsuitable for real-world applications, due to their massive computational cost, high memory bandwidth, and long latency.
Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion
We introduce DeepInversion, a new method for synthesizing images from the image distribution used to train a deep neural network.
STEERAGE: Synthesis of Neural Networks Using Architecture Search and Grow-and-Prune Methods
On MNIST dataset, our CNN architecture achieves an error rate of 0. 66%, with 8. 6x fewer parameters compared to the LeNet-5 baseline.
DiabDeep: Pervasive Diabetes Diagnosis based on Wearable Medical Sensors and Efficient Neural Networks
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.
SPRING: A Sparsity-Aware Reduced-Precision Monolithic 3D CNN Accelerator Architecture for Training and Inference
To take advantage of sparsity, some accelerator designs explore sparsity encoding and evaluation on CNN accelerators.
Hardware Architecture
SECRET: Semantically Enhanced Classification of Real-world Tasks
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.
Incremental Learning Using a Grow-and-Prune Paradigm with Efficient Neural Networks
Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications.
SCANN: Synthesis of Compact and Accurate Neural Networks
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.
Software-defined Design Space Exploration for an Efficient DNN Accelerator Architecture
It models the accelerator design task as a multi-dimensional optimization problem.
Hardware-Guided Symbiotic Training for Compact, Accurate, yet Execution-Efficient LSTM
In this work, we propose a hardware-guided symbiotic training methodology for compact, accurate, yet execution-efficient inference models.
ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation
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.
Grow and Prune Compact, Fast, and Accurate LSTMs
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.
NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm
To address these problems, we introduce a network growth algorithm that complements network pruning to learn both weights and compact DNN architectures during training.
