79 citations · 383 across the 28 of their papers we have counts for
12 papers · 1 filter
The Architectural Implications of Distributed Reinforcement Learning on CPU-GPU Systems
Ahmet Inci, Evgeny Bolotin, Yaosheng Fu +4
With deep reinforcement learning (RL) methods achieving results that exceed human capabilities in games, robotics, and simulated environments, continued scaling of RL training is c…
One Weight Bitwidth to Rule Them All
Ting-Wu Chin, Pierce I-Jen Chuang, Vikas Chandra +1
Weight quantization for deep ConvNets has shown promising results for applications such as image classification and semantic segmentation and is especially important for applicatio…
Renofeation: A Simple Transfer Learning Method for Improved Adversarial Robustness
Ting-Wu Chin, Cha Zhang, Diana Marculescu
Fine-tuning through knowledge transfer from a pre-trained model on a large-scale dataset is a widely spread approach to effectively build models on small-scale datasets. In this wo…
Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization
Dimitrios Stamoulis, Ruizhou Ding, Di Wang +4
Can we reduce the search cost of Neural Architecture Search (NAS) from days down to only few hours? NAS methods automate the design of Convolutional Networks (ConvNets) under hardw…
Single-Path NAS: Device-Aware Efficient ConvNet Design
Dimitrios Stamoulis, Ruizhou Ding, Di Wang +4
Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the latency constraint of a mobile device? Neural Architecture Se…
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
Dimitrios Stamoulis, Ruizhou Ding, Di Wang +4
Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the runtime constraint of a mobile device? Neural architecture se…
Hardware-Aware Machine Learning: Modeling and Optimization
Diana Marculescu, Dimitrios Stamoulis, Ermao Cai
Recent breakthroughs in Deep Learning (DL) applications have made DL models a key component in almost every modern computing system. The increased popularity of DL applications dep…
Designing Adaptive Neural Networks for Energy-Constrained Image Classification
Dimitrios Stamoulis, Ting-Wu Chin, Anand Krishnan Prakash +4
As convolutional neural networks (CNNs) enable state-of-the-art computer vision applications, their high energy consumption has emerged as a key impediment to their deployment on e…
Tractable Learning and Inference for Large-Scale Probabilistic Boolean Networks
Ifigeneia Apostolopoulou, Diana Marculescu
Probabilistic Boolean Networks (PBNs) have been previously proposed so as to gain insights into complex dy- namical systems. However, identification of large networks and of the un…
HyperPower: Power- and Memory-Constrained Hyper-Parameter Optimization for Neural Networks
Dimitrios Stamoulis, Ermao Cai, Da-Cheng Juan +1
While selecting the hyper-parameters of Neural Networks (NNs) has been so far treated as an art, the emergence of more complex, deeper architectures poses increasingly more challen…
Machine Learning and Manycore Systems Design: A Serendipitous Symbiosis
Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande +2
Tight collaboration between experts of machine learning and manycore system design is necessary to create a data-driven manycore design framework that integrates both learning and…
NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks
Ermao Cai, Da-Cheng Juan, Dimitrios Stamoulis +1
"How much energy is consumed for an inference made by a convolutional neural network (CNN)?" With the increased popularity of CNNs deployed on the wide-spectrum of platforms (from…