50 citations · 389 across the 39 of their papers we have counts for
9 papers · 1 filter
STEERAGE: Synthesis of Neural Networks Using Architecture Search and Grow-and-Prune Methods
Shayan Hassantabar, Xiaoliang Dai, Niraj K. Jha
Neural networks (NNs) have been successfully deployed in many applications. However, architectural design of these models is still a challenging problem. Moreover, neural networks…
Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion
Hongxu Yin, Pavlo Molchanov, Zhizhong Li +5
We introduce DeepInversion, a new method for synthesizing images from the image distribution used to train a deep neural network. We 'invert' a trained network (teacher) to synthes…
DiabDeep: Pervasive Diabetes Diagnosis based on Wearable Medical Sensors and Efficient Neural Networks
Hongxu Yin, Bilal Mukadam, Xiaoliang Dai +1
Diabetes impacts the quality of life of millions of people. However, diabetes diagnosis is still an arduous process, given that the disease develops and gets treated outside the cl…
SPRING: A Sparsity-Aware Reduced-Precision Monolithic 3D CNN Accelerator Architecture for Training and Inference
Ye Yu, Niraj K. Jha
CNNs outperform traditional machine learning algorithms across a wide range of applications. However, their computational complexity makes it necessary to design efficient hardware…
Incremental Learning Using a Grow-and-Prune Paradigm with Efficient Neural Networks
Xiaoliang Dai, Hongxu Yin, Niraj K. Jha
Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications. However, their fixed architecture, substantial training cost, and signif…
SECRET: Semantically Enhanced Classification of Real-world Tasks
Ayten Ozge Akmandor, Jorge Ortiz, Irene Manotas +2
Supervised machine learning (ML) algorithms are aimed at maximizing classification performance under available energy and storage constraints. They try to map the training data to…
SCANN: Synthesis of Compact and Accurate Neural Networks
Shayan Hassantabar, Zeyu Wang, Niraj K. Jha
Deep neural networks (DNNs) have become the driving force behind recent artificial intelligence (AI) research. An important problem with implementing a neural network is the design…
Software-defined Design Space Exploration for an Efficient DNN Accelerator Architecture
Ye Yu, Yingmin Li, Shuai Che +2
Deep neural networks (DNNs) have been shown to outperform conventional machine learning algorithms across a wide range of applications, e.g., image recognition, object detection, r…
Hardware-Guided Symbiotic Training for Compact, Accurate, yet Execution-Efficient LSTM
Hongxu Yin, Guoyang Chen, Yingmin Li +3
Many long short-term memory (LSTM) applications need fast yet compact models. Neural network compression approaches, such as the grow-and-prune paradigm, have proved to be promisin…