CAVIAR: A 45k Neuron, 5M Synapse, 12G Connects/s AER Hardware Sensory–Processing– Learning–Actuating System for High-Speed Visual Object Recognition and Tracking

By R. Serrano-Gotarredona, M. Oster, P. Lichtsteiner, A. Linares-Barranco, R. Paz-Vicente, F. Gomez-Rodriguez, Luis A. Camuñas-Mesa, R. Berner, Manuel Rivas Pérez, Tobi Delbruck and 8 more. 2009

326 citations recorded by the source corpus.

Subfields: Cellular and Molecular Neuroscience, Electrical and Electronic Engineering

How researchers see this paper

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

In Cellular and Molecular Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

Deep learning in neural networks: An overview (2014, neutral): “Future energyefficient hardware for DL in NNs may implement aspects of such models; see (e.g., Liu et al., 2001; Roggen et al., 2003; Glackin et al., 2005; Fieres et al., 2008; Khan et al., 2008; Serrano-Gotarredona et al., 2009; Jin et al., 2010; Neil and Liu, 2014).”
Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing (2015, methodology): “The CAVIAR system [14] used a network of convolution and competition chips to process visual events and recognize objects within milliseconds, and improved convolution chips with larger kernels and lower latency were presented in [26].”
Convolutional networks and applications in vision (2010, background): “CAVIAR is the leading such project, with a performance of 12G connections/sec [49].”
Neuromorphic Electronic Circuits for Building Autonomous Cognitive Systems (2014, methodology): “ail. These circuits have been integrated into Very Large Scale Integration (VLSI) devices for building real-time sensory-motor systems and robotic demonstrators of neural computing architectures [14]–[19]. However, these systems, synthesized using ad-hoc methods, could only implement very speciﬁc se”
Finding a roadmap to achieve large neuromorphic hardware systems (2013, methodology): “…is making its ﬁrst serious approaches toward large-scale neuromorphic hardware [e.g., FACETs (Schemmel et al., 2008a), DARPA SyNAPSE, Caviar (Serrano-Gotarredona et al., 2009)], a neuromorphic hardware roadmap could be seen as a way through the foreseen upcoming bottle-necks (Marr et al.,…”
Event-Based Vision: A Survey (2019, methodology): “An event-driven update of the position of a model of the object shape was used to detect and track objects with a known simple shape, such as a blob [6], circle [53], [205] or line [54].”
HOTS: A Hierarchy of Event-Based Time-Surfaces for Pattern Recognition (2017, methodology): “Architecture for Real-time (CAVIAR) project [11] which recognizes and tracks circles of different sizes using a hierarchical spiking network running on custom hardware.”