论文信息 - An interconnection architecture for integrate and fire neuromorphic multi-chip networks

An interconnection architecture for integrate and fire neuromorphic multi-chip networks

The availability of large neuromorphic electronic systems can represent a really useful tool to deeply and effectively investigate on innovative, “bio-inspired”, computational paradigms. Among the others, one of the main obstacles in implementation of large networks is represented by the limited silicon area available on a chip that requires further efforts to design interconnected architectures. A particular strategy to reduce the I/O analogue pins well suited for neuromorphic multi chip architecture will be presented.

Vincenzo Bonaiuto | Fausto Sargeni

[1] Tobi Delbrück,et al. A Multichip Pulse-Based Neuromorphic Infrastructure and Its Application to a Model of Orientation Selectivity , 2007, IEEE Transactions on Circuits and Systems I: Regular Papers.

[2] R. Douglas,et al. A multi-chip pulse-based neuromorphic infrastructure and its application to a cortical model of orientation selectivity , 2006 .

[3] Patrick Camilleri,et al. A Neuromorphic aVLSI network chip with configurable plastic synapses , 2007, 7th International Conference on Hybrid Intelligent Systems (HIS 2007).

[4] Juan López Coronado,et al. AER Neuro-Inspired interface to Anthropomorphic Robotic Hand , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[5] Massimiliano Giulioni,et al. An aVLSI recurrent network of spiking neurons with reconfigurable and plastic synapses , 2006, 2006 IEEE International Symposium on Circuits and Systems.

[6] Carver Mead,et al. Analog VLSI and neural systems , 1989 .

[7] Kenneth R. Laker,et al. Design of analog integrated circuits and systems , 1994 .

[8] Vittorio Dante,et al. A VLSI recurrent network of integrate-and-fire neurons connected by plastic synapses with long-term memory , 2003, IEEE Trans. Neural Networks.