Multi-chip Integrate and Fire neural network architecture

In the field of the Artificial Neural Networks, multi-chip architecture can be effectively used to implement very large networks. The availability of large neural electronic systems can represent a really useful tool to deeply and effectively investigate on innovative, “bio-inspired”, computational paradigms. In this paper, the authors present a technique to reduce the I/O analogue pins of about 87%, previously applied from the authors to Cellular Neural Networks, well suited for neuromorphic neural networks.

[1]  Fausto Sargeni,et al.  A 6 x 6 Cells Interconnection-Oriented Programmable Chip for CNN , 1998 .

[2]  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.

[3]  W. Guggenbuhl,et al.  On charge injection in analog MOS switches and dummy switch compensation techniques , 1990 .

[4]  Vincenzo Bonaiuto,et al.  An interconnection architecture for integrate and fire neuromorphic multi-chip networks , 2009, 2009 52nd IEEE International Midwest Symposium on Circuits and Systems.

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

[6]  Fausto Sargeni,et al.  A 720 cells interconnection-oriented system for cellular neural networks , 1997, Proceedings of 1997 IEEE International Symposium on Circuits and Systems. Circuits and Systems in the Information Age ISCAS '97.

[7]  Fausto Sargeni,et al.  A Dedicated Multi-Chip Programmable System for Cellular Neural Networks , 1999 .

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

[9]  Behzad Razavi,et al.  Design of Analog CMOS Integrated Circuits , 1999 .

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

[11]  Fausto Sargeni,et al.  An improved architecture for the interconnections in a multi-chip CNN system , 1998, ISCAS '98. Proceedings of the 1998 IEEE International Symposium on Circuits and Systems (Cat. No.98CH36187).

[12]  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.

[13]  Fausto Sargeni.  Digitally programmable transconductance amplifier for CNN applications , 1994 .

[14]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[15]  Sergio Taraglio,et al.  A dedicated hardware system for CNN stereo vision , 1999, ISCAS'99. Proceedings of the 1999 IEEE International Symposium on Circuits and Systems VLSI (Cat. No.99CH36349).

[16]  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.

[17]  Giacomo Indiveri,et al.  A low-power adaptive integrate-and-fire neuron circuit , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[18]  Fausto Sargeni,et al.  A 3 × 3 digitally programmable CNN chip , 1996 .

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

[20]  Vincenzo Bonaiuto,et al.  A fully digitally programmable CNN chip , 1995 .

[21]  Kari Halonen,et al.  CMOS Current Amplifiers: Speed versus Nonlinearity , 2010 .

[22]  Fausto Sargeni,et al.  A 9/spl times/9 multi-chip board for cellular neural networks , 1996, 1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96).

[23]  Fausto Sargeni,et al.  A 6 × 6 Cells Interconnection-Oriented Programmable Chip for CNN , 1998 .