Alert button
Picture for Diana Marculescu

Diana Marculescu

Alert button

Understanding the Impact of Label Granularity on CNN-based Image Classification

Jan 21, 2019
Zhuo Chen, Ruizhou Ding, Ting-Wu Chin, Diana Marculescu

Figure 1 for Understanding the Impact of Label Granularity on CNN-based Image Classification
Figure 2 for Understanding the Impact of Label Granularity on CNN-based Image Classification
Figure 3 for Understanding the Impact of Label Granularity on CNN-based Image Classification
Figure 4 for Understanding the Impact of Label Granularity on CNN-based Image Classification
Viaarxiv icon

Learning-based Application-Agnostic 3D NoC Design for Heterogeneous Manycore Systems

Oct 20, 2018
Biresh Kumar Joardar, Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu

Figure 1 for Learning-based Application-Agnostic 3D NoC Design for Heterogeneous Manycore Systems
Figure 2 for Learning-based Application-Agnostic 3D NoC Design for Heterogeneous Manycore Systems
Figure 3 for Learning-based Application-Agnostic 3D NoC Design for Heterogeneous Manycore Systems
Figure 4 for Learning-based Application-Agnostic 3D NoC Design for Heterogeneous Manycore Systems
Viaarxiv icon

Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks

Oct 18, 2018
Ting-Wu Chin, Cha Zhang, Diana Marculescu

Figure 1 for Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks
Figure 2 for Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks
Figure 3 for Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks
Figure 4 for Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks
Viaarxiv icon

Hardware-Aware Machine Learning: Modeling and Optimization

Sep 14, 2018
Diana Marculescu, Dimitrios Stamoulis, Ermao Cai

Figure 1 for Hardware-Aware Machine Learning: Modeling and Optimization
Figure 2 for Hardware-Aware Machine Learning: Modeling and Optimization
Figure 3 for Hardware-Aware Machine Learning: Modeling and Optimization
Figure 4 for Hardware-Aware Machine Learning: Modeling and Optimization
Viaarxiv icon

Designing Adaptive Neural Networks for Energy-Constrained Image Classification

Aug 07, 2018
Dimitrios Stamoulis, Ting-Wu Chin, Anand Krishnan Prakash, Haocheng Fang, Sribhuvan Sajja, Mitchell Bognar, Diana Marculescu

Figure 1 for Designing Adaptive Neural Networks for Energy-Constrained Image Classification
Figure 2 for Designing Adaptive Neural Networks for Energy-Constrained Image Classification
Figure 3 for Designing Adaptive Neural Networks for Energy-Constrained Image Classification
Figure 4 for Designing Adaptive Neural Networks for Energy-Constrained Image Classification
Viaarxiv icon

Tractable Learning and Inference for Large-Scale Probabilistic Boolean Networks

Jan 23, 2018
Ifigeneia Apostolopoulou, Diana Marculescu

Figure 1 for Tractable Learning and Inference for Large-Scale Probabilistic Boolean Networks
Figure 2 for Tractable Learning and Inference for Large-Scale Probabilistic Boolean Networks
Figure 3 for Tractable Learning and Inference for Large-Scale Probabilistic Boolean Networks
Figure 4 for Tractable Learning and Inference for Large-Scale Probabilistic Boolean Networks
Viaarxiv icon

HyperPower: Power- and Memory-Constrained Hyper-Parameter Optimization for Neural Networks

Dec 06, 2017
Dimitrios Stamoulis, Ermao Cai, Da-Cheng Juan, Diana Marculescu

Figure 1 for HyperPower: Power- and Memory-Constrained Hyper-Parameter Optimization for Neural Networks
Figure 2 for HyperPower: Power- and Memory-Constrained Hyper-Parameter Optimization for Neural Networks
Figure 3 for HyperPower: Power- and Memory-Constrained Hyper-Parameter Optimization for Neural Networks
Figure 4 for HyperPower: Power- and Memory-Constrained Hyper-Parameter Optimization for Neural Networks
Viaarxiv icon

LightNN: Filling the Gap between Conventional Deep Neural Networks and Binarized Networks

Dec 02, 2017
Ruizhou Ding, Zeye Liu, Rongye Shi, Diana Marculescu, R. D. Blanton

Figure 1 for LightNN: Filling the Gap between Conventional Deep Neural Networks and Binarized Networks
Figure 2 for LightNN: Filling the Gap between Conventional Deep Neural Networks and Binarized Networks
Figure 3 for LightNN: Filling the Gap between Conventional Deep Neural Networks and Binarized Networks
Figure 4 for LightNN: Filling the Gap between Conventional Deep Neural Networks and Binarized Networks
Viaarxiv icon

Machine Learning and Manycore Systems Design: A Serendipitous Symbiosis

Nov 30, 2017
Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu

Figure 1 for Machine Learning and Manycore Systems Design: A Serendipitous Symbiosis
Figure 2 for Machine Learning and Manycore Systems Design: A Serendipitous Symbiosis
Figure 3 for Machine Learning and Manycore Systems Design: A Serendipitous Symbiosis
Figure 4 for Machine Learning and Manycore Systems Design: A Serendipitous Symbiosis
Viaarxiv icon

NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks

Oct 15, 2017
Ermao Cai, Da-Cheng Juan, Dimitrios Stamoulis, Diana Marculescu

Figure 1 for NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks
Figure 2 for NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks
Figure 3 for NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks
Figure 4 for NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks
Viaarxiv icon