A Scalable Parallel Formulation of the Backpropagation Algorithm for Hypercubes and Related Architectures

By Vipin Kumar, Shashi Shekhar, M. Amin. 1994

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Guillaume Bellec
2. Chen Liu
3. Matthew F. Dixon
4. Robert A. Legenstein
5. Wolfgang Maass
6. B. Vogginger
7. David Kappel
8. Johannes Partzsch

Citations in the corpus

• Classification-based financial markets prediction using deep neural networks (2016, methodology): “o n 1 do 13: E E + E i(w ) 14: end for 15: end while 2.1 Mini-batching It is well known that mini-batching improves the computational performance of the feedforward and back-propagation computations (Shekhar and Amin, 1994; Li et al., 2014). We process b observations in one mini-batch. This results ”
• Artificial neural networks in hardware: A survey of two decades of progress (2010, unknown): “, MLP with back propagation [77,78], radial basis function networks [79,31,80], and Neocognitron [81]), and neurocomputers [49,82].”
• Memory-Efficient Deep Learning on a SpiNNaker 2 Prototype (2018, methodology): “This so-called checkerboarding 2D partition method is proved to be more efficient than 1D partition (Kumar et al., 1994).”