Special-purpose digital hardware for neural networks: An architectural survey

By P. Ienne, T. Cornu, G. Kuhn. 1996

How researchers see this paper

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

GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding (2020, background): “To address such a demand, special hardware (chips and networked machines) built for neural network training and inference can be dated back to 25 years ago (Ienne et al., 1996).”
Structure-Adaptable Digital Neural Networks (1999, background): “of standard microprocessor chips and the emergence of new and faster algorithms tends to favor this last approach [98].”
Artificial neural networks in hardware: A survey of two decades of progress (2010, unknown): “Ienne et al. [52] present a survey of digital implementations by considering two basic designs: Parallel systems with standard digital components and parallel systems with custom processors.”