No Access

Vast Topological Learning and Sentient AGI

Imagination Engines, Inc., 1550 Wall Street, St. Charles, Missouri 63303, USA

E-mail Address: sthaler@imagination-engines.com

https://doi.org/10.1142/S2705078521500053Cited by:4 (Source: Crossref)

Abstract

A novel form of neurocomputing allows machines to generate new concepts along with their anticipated consequences, all encoded as chained associative memories. Knowledge is accumulated by the system through direct experience as network chaining topologies form in response to various environmental input patterns. Thereafter, random disturbances to the connections joining these nets promote the formation of alternative chaining topologies representing novel concepts. The resulting ideational chains are then reinforced or weakened as they incorporate nets containing memories of impactful events or things. Such encodings of entities, actions, and relationships as geometric forms composed of artificial neural nets may well suggest how the human brain summarizes and appraises the states of nearly a hundred billion cortical neurons. It may also be the paradigm that allows the scaling of synthetic neural systems to brain-like proportions to achieve sentient artificial general intelligence (SAGI).

Keywords:

References

Abbott, R. [2020] The Reasonable Robot: Artificial Intelligence and the Law (Cambridge University Press, Cambridge). Crossref, Google Scholar
Braitenberg, V. [1977] On the Texture of Brains (Springer, Berlin). Crossref, Google Scholar
Bridle, J. S. [1989] Soulié, F. F. & J. Hérault (eds.). Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition, Neurocomputing 68, 227–236 (Springer, Berlin), https://doi.org/10.1007/978-3-642-76153-9_28. Google Scholar
Bringsjord, S., Bello, P. and Ferrucci, D. [2001] Creativity, the Turing test, and the (better) Lovelace test, Minds Mach. 11, 3–27. Crossref, Google Scholar
Clark, A. [1991] Microcognition: Philosophy, Cognitive Science, and Parallel Distributed Processing (MIT, Cambridge). Crossref, Google Scholar
Crick, F. [1984] Function of the thalamic reticular complex: The searchlight hypothesis, Proc. Natl. Acad. Sci. USA 81, 4586–4590. pmid:6589612. Crossref, Google Scholar
Hebb, D. O. [1949] The Organization of Behavior (Wiley, New York). Google Scholar
Hecht-Nielsen, R. [2005] Confabulation Theory: The Mechanism of Thought (Springer, New York). Google Scholar
Josephson, J. R. and Josephson, S. G. (eds.) [1994] Abductive Inference: Computation, Philosophy, Technology (Cambridge, UK). Crossref, Google Scholar
Justice Potter Stewart [1964] in Jacobellis v. Ohio, 378 U.S. 184. Google Scholar
Kilner, J. and Lemon, R. [2013] What We Currently Know About Mirror Neurons. Minireview (Elsevier). http://dx.doi.org/10.1016/j.cub.2013.10.051. Google Scholar
Minati, G. and Vitiello, G. [2006] Mistake Making Machines. Minati, G., E. Pessa & M. Abram (eds.) Systemics of Emergence: Research and Development (Springer, Boston), https://doi.org/10.1007/0-387-28898-8_4. Crossref, Google Scholar
Palm, G. [1982] Neural Assemblies. An Alternative Approach to Artificial Intelligence (Springer, New York). Crossref, Google Scholar
Peitgen, H. and Saupe, D. (eds.) [1988] The Science of Fractal Images (Springer-Verlag, New York). Google Scholar
Rumelhart, D. E., Hinton, G. E. and Williams, R. J. [1986] Learning internal representations by error propagation, in Parallel Distributed Processing, Vol. 1: Foundations (MIT Press, Cambridge). Google Scholar
Thaler, S. L. [1996] “A proposed symbolism for network-implemented discovery processes,” in Proc. World Congress on Neural Networks (Mahwah, NJ, Lawrence Erlbaum), pp. 1265–1268. Google Scholar
Thaler, S. L. [1997] U.S. Patent No. 5,659,666, Device for the autonomous generation of useful information, Washington, DC: U.S. Patent and Trademark Office. Google Scholar
Thaler, S. L. [1998] Predicting ultra-hard binary compounds via cascaded auto- and hetero-associative neural networks, J. Alloys Compd. 279, 47–59. Crossref, Google Scholar
Thaler, S. L. [2008] U.S. Patent No. 7,454,388, Device for the autonomous bootstrapping of useful information, Washington, DC: U.S. Patent and Trademark Office. Google Scholar
Thaler, S. L. [2013] The creativity machine paradigm, Carayannis, E. G. (ed.) Encyclopedia of Creativity, Invention, Innovation, and Entrepreneurship (Springer Science + Business, New York), pp. 447–456. Crossref, Google Scholar
Thaler, S. L. [2014] Synaptic perturbation and consciousness, Int. J. Mach. Consciousness 6(2), 75–107. Link, Google Scholar
Thaler, S. L. [2016a] Cycles of insanity and creativity within contemplative neural systems, Med. Hypotheses 94, 138–147. Crossref, Google Scholar
Thaler S. L. [2016b] Pattern turnover in synaptically perturbed neural systems, Procedia Comput. Sci. 88, 21–26. Crossref, Google Scholar
Thaler, S. L. [2019] U.S. Patent No. 10,423,875, Electro-optical device and method for identifying and inducing topological states formed among interconnecting neural modules, Washington, DC: U.S. Patent and Trademark Office. Google Scholar
Wei, X. [2009] “Research of neural networks in image anomaly identification application,” in Proc. 2009 3rd International Conference on Teaching and Computational Science. Google Scholar
Wolfram, S. [2002] A New Kind of Science (Wolfram Media, Champaign), 1-57955-008-8. Google Scholar
Zhang, B., Fu, M., Yan, H. and Jabri, M. [1999] Handwritten digit recognition by adaptive-subspace self-organizing map (ASSOM), IEEE Trans. Neural Netw. 10(4), 939–945, https://doi.org/10.1109/72.774267. Crossref, Google Scholar
Zikopoulos, B. and Barbas, H. [2006] Prefrontal projections to the thalamic reticular nucleus form a unique circuit for attentional mechanisms, J. Neurosci. 26(28), 7348–7361. Crossref, Google Scholar