Utilizing Geometric Anomalies of High Dimension: When Complexity Makes Computation Easier
@inproceedings{Kainen1997UtilizingGA, title={Utilizing Geometric Anomalies of High Dimension: When Complexity Makes Computation Easier}, author={P. C. Kainen}, year={1997} }
Just as a busy kitchen can be more efficient than an idle one, Kleinrock showed 35 years ago that heavily used networks admit simple heuristic approximations with excellent quantitative accuracy. We describe a number of different examples in which having many parameters actually facilitates computation and we suggest connections with geometric phenomena in high-dimensional spaces. It seems that in several interesting and quite general situations, dimensionality may be a blessing in disguise… CONTINUE READING
22 Citations
Bringing the Blessing of Dimensionality to the Edge
- Computer Science
- 2019 1st International Conference on Industrial Artificial Intelligence (IAI)
- 2019
- 1
- PDF
Some insights from high-dimensional spheres: Comment on "The unreasonable effectiveness of small neural ensembles in high-dimensional brain" by Alexander N. Gorban et al.
- Computer Science, Medicine
- Physics of life reviews
- 2019
- 5
- PDF
Blessing of dimensionality: mathematical foundations of the statistical physics of data
- Computer Science, Medicine
- Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
- 2018
- 48
- PDF
High-Dimensional Brain in a High-Dimensional World: Blessing of Dimensionality
- Computer Science, Medicine
- Entropy
- 2020
- 10
- PDF
The unreasonable effectiveness of small neural ensembles in high-dimensional brain
- Computer Science, Biology
- Physics of life reviews
- 2018
- 24
- PDF
Kernel Stochastic Separation Theorems and Separability Characterizations of Kernel Classifiers
- Mathematics, Computer Science
- 2019 International Joint Conference on Neural Networks (IJCNN)
- 2019
- 1
Fast Construction of Correcting Ensembles for Legacy Artificial Intelligence Systems: Algorithms and a Case Study
- Computer Science
- Inf. Sci.
- 2019
- 8
- PDF
References
SHOWING 1-10 OF 22 REFERENCES
Worst-Case Performance Bounds for Simple One-Dimensional Packing Algorithms
- Mathematics, Computer Science
- SIAM J. Comput.
- 1974
- 827
- PDF
Sphere Packings, Lattices and Groups
- Mathematics, Computer Science
- Grundlehren der mathematischen Wissenschaften
- 1988
- 3,317
- PDF
Expected Wire Length between Two Randomly Chosen Terminals
- Mathematics, Computer Science
- SIAM Rev.
- 1995
- 11
Estimates of the Number of Hidden Units and Variation with Respect to Half-Spaces
- Mathematics, Medicine
- Neural Networks
- 1997
- 95
- PDF
A geometric method to obtain error-correcting classification by neural networks with fewer hidden units
- Computer Science
- Proceedings of International Conference on Neural Networks (ICNN'96)
- 1996
- 3
Some unexpected expected behavior results for bin packing
- Mathematics, Computer Science
- STOC '84
- 1984
- 71
Universal approximation bounds for superpositions of a sigmoidal function
- Mathematics, Computer Science
- IEEE Trans. Inf. Theory
- 1993
- 2,322
- PDF