caa a22 4500 465742483 CHVBK 20180323111811.0 cr unu---uuuuu 170327e19900401xx s 000 0 eng 10.1007/BF00929928 doi (NATIONALLICENCE)springer-10.1007/BF00929928 Scalable VLSI implementations for neural networks [Elektronische Daten] [D. van den Bout, P. Franzon, J. Paulos, T. Miller, W. Snyder, T. Nagle, W. Liu] This paper discusses research on scalable VLSI implementations of feed-forward and recurrent neural networks. These two families of networks are useful in a wide variety of important applications—classification tasks for feed-forward nets and optimization problems for recurrent nets—but their differences affect the way they should be built. We find that analog computation with digitally programmable weights works best for feed-forward networks, while stochastic processing takes advantage of the integrative nature of recurrent networks. We have shown early prototypes of these networks which compute at rates of 1-2 billion connections per second. These general-purpose neural building blocks can be coupled with an overall data transmission framework that is electronically reconfigured in a local manner to produce arbitrarily large, fault-tolerant networks. Kluwer Academic Publishers, 1990 van den Bout D. Department of Electrical and Computer Engineering, North Carolina State University, USA aut Franzon P. Department of Electrical and Computer Engineering, North Carolina State University, USA aut Paulos J. Department of Electrical and Computer Engineering, North Carolina State University, USA aut Miller T. Department of Electrical and Computer Engineering, North Carolina State University, USA aut Snyder W. Department of Electrical and Computer Engineering, North Carolina State University, USA aut Nagle T. Department of Electrical and Computer Engineering, North Carolina State University, USA aut Liu W. Department of Electrical and Computer Engineering, North Carolina State University, USA aut Journal of VLSI signal processing systems for signal, image and video technology Springer Netherlands 1/4(1990-04-01), 367-385 0922-5773 1:4<367 1990 1 11265 https://doi.org/10.1007/BF00929928 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF00929928 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- van den Bout D. Department of Electrical and Computer Engineering, North Carolina State University, USA aut NATIONALLICENCE 700 1- Franzon P. Department of Electrical and Computer Engineering, North Carolina State University, USA aut NATIONALLICENCE 700 1- Paulos J. Department of Electrical and Computer Engineering, North Carolina State University, USA aut NATIONALLICENCE 700 1- Miller T. Department of Electrical and Computer Engineering, North Carolina State University, USA aut NATIONALLICENCE 700 1- Snyder W. Department of Electrical and Computer Engineering, North Carolina State University, USA aut NATIONALLICENCE 700 1- Nagle T. Department of Electrical and Computer Engineering, North Carolina State University, USA aut NATIONALLICENCE 700 1- Liu W. Department of Electrical and Computer Engineering, North Carolina State University, USA aut NATIONALLICENCE 773 0- Journal of VLSI signal processing systems for signal, image and video technology Springer Netherlands 1/4(1990-04-01), 367-385 0922-5773 1:4<367 1990 1 11265 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer