23 citations · 60 across the 14 of their papers we have counts for
4 papers · 1 filter
Elastic Neural Networks for Classification
Yi Zhou, Yue Bai, Shuvra S. Bhattacharyya +1
In this work we propose a framework for improving the performance of any deep neural network that may suffer from vanishing gradients. To address the vanishing gradient issue, we s…
Generalized Graph Connections for Dataflow Modeling of DSP Applications
Yanzhou Liu, Lee Barford, Shuvra S. Bhattacharyya
In dataflow representations for signal processing systems, applications are represented as directed graphs in which vertices represent computations and edges correspond to buffers…
Elastic Neural Networks: A Scalable Framework for Embedded Computer Vision
Yue Bai, Shuvra S. Bhattacharyya, Antti P. Happonen +1
We propose a new framework for image classification with deep neural networks. The framework introduces intermediate outputs to the computational graph of a network. This enables f…
PRUNE: Dynamic and Decidable Dataflow for Signal Processing on Heterogeneous Platforms
Jani Boutellier, Jiahao Wu, Heikki Huttunen +1
The majority of contemporary mobile devices and personal computers are based on heterogeneous computing platforms that consist of a number of CPU cores and one or more Graphics Pro…