Machine intelligence through 3D waferscale integration | IEEE Conference Publication | IEEE Xplore

Machine intelligence through 3D waferscale integration


Abstract:

Bringing computing systems to the stage of Machine Intelligence will require a massive scaling in processing, memory, and interconnectivity, and thus a major change in ho...Show More

Abstract:

Bringing computing systems to the stage of Machine Intelligence will require a massive scaling in processing, memory, and interconnectivity, and thus a major change in how electronic systems are designed. Long overlooked because of its unsuitability for the exacting demands of enterprise computing, 3D waferscale integration offers a promising scaling path, due in large part to the fault-tolerant nature of many cognitive algorithms. This work explores this scaling path in greater detail, invoking a simple model of brain connectivity to examine the potential for 3D waferscale integration to meet the demanding interconnectivity requirements of Machine Intelligence.
Date of Conference: 16-19 October 2017
Date Added to IEEE Xplore: 08 March 2018
ISBN Information:
Conference Location: Burlingame, CA, USA
References is not available for this document.

I. Introduction

Computing systems have made tremendous strides in the area of cognitive computing, evolving from transactional processing to tasks requiring fuzzier analysis such as classification, pattern recognition, and anomaly detection [1]. At the algorithm level, these advances fall under the broad category of Machine Learning, characterized by solving a specific task by defining and optimizing an objective function. In Deep Learning, a particular area of Machine Learning, a large network having fixed connectivity is trained to a specific task using large amounts of labeled data.

Select All
1.
J.E. Kelly III and S. Hamm, Smart Machines. New York : Columbia University Press, 2013.
2.
Q. Wen and D.B. Chklovskii, “Segregation of the brain into gray and white matter: A design minimizing conduction delays,” PLoS Comp. Bio., vol. 1, p. e78, 2005.
3.
J. Hawkins and S. Ahmad, “Why neurons have thousands of synapses, a theory of sequence memory in neocortex,” Frontiers in Neural Circuits, vol. 10, 2015.
4.
J. Hasler and B. Marr. “Finding a roadmap to achieve large neuromorphic hardware systems,” Frontiers in Neurosci., vol. 7, 2013.
5.
C. Mead, “Neuromorphic electronic systems, Proc. IEEE, vol. 78, pp. 1629–1636, 1990.
6.
P. Batude, “3DVLSI with CoolCube process: An alternative path to scaling,” in Proc. IEEE Symp. on VLSI Tech., pp. T48–T49, 2015.
7.
W. Lin, “Prototype of multi-stacked memory wafers using low-temperature oxide bonding and ultra-fine-dimension copper through-silicon-via interconnects,” in Proc. IEEE SOI-3D-Subthreshold Microelectronics Tech. Unified Con/(S3S'14), pp. 1–3, 2014.
8.
A. Kumar, “Toward human-scale brain computing using 3D wafer scale integration.” ACM Journal on Emerging Technologies in Computing Systems, vol. 13, 2017.
9.
B. Hellwig, “A quantitative analysis of the local connectivity between pyramidal neurons in layers 2/3 of the rat visual cortex,” Biological Cybernetics, vol. 82, pp. 111–121, 2000.
10.
D.S. Bassett and E. Bullmore, “Small-world brain networks,” The Neuroscientist, vol. 12, pp. 512–523, 2006.
11.
J.S. Meena, “Overview of emerging nonvolatile memory technologies,” Nanoscale Research Lett., vol. 9, pp. 1–33, 2014.

Contact IEEE to Subscribe

References

References is not available for this document.