Superintelligent AI Systems

Source: Deep Learning on Medium

Superintelligent AI Systems

I have always been convinced that the only way to get artificial intelligence to work is to do the computation in a way similar to the human brain. That is the goal I have been pursuing. We are making progress, though we still have lots to learn about how the brain actually works.” — Geoffrey Hinton

Artificial intelligence will reach human levels by around 2029. Follow that out further to, say, 2045, we will have multiplied the intelligence, the human biological machine intelligence of our civilization a billion-fold. — Ray Kurzweil

Having established the scientific facts that prove the existing set of Activation Functions such as SIGMOID, TANH, SOFTMAX, RELU, LEAKY RELU among others neither EMANATED from the TRAINING DAT, TESTING DATA nor from our REFERENCED AI-ML-PURIFIED DATA SET. However, their humble background was just “ARBITRARY ASSUMPTIONS” with the help of “TRIAL AND ERROR”.

Jamilu (2019) proposed “Rules of Thumb” called “Jameel’s ANNAF Stochastic Criterion” and “Jameel’s ANNAF Deterministic Criterion” for choices of Activation Functions. One of these Criterion’s axioms proposed that we must establish RELATIONSHIP between the Neural Networks’ SET OF ACTIVATION FUNCTIONS and our REFERENCED AI DATA SET, to establish this kind relationship, henceforth Activation Functions shall be EMANATED FROM OUR REFERENCED AI DATA SET. This also revealed that the Advanced optimized Activation Functions satisfies Jameel’s ANNAF Stochastic or and Deterministic Criterion would depend on the REFERENCED PURIFIED AI DATA SET, TIME CHANGE and AREA OF APPLICATION (acronym DTA).

Jamilu (2019) discovered that we can have up to TWO THOUSAND (2000) Activation Functions Emanated from a single AI Data Sample using Jameel’s ANNAF Deterministic Criterion, this is an incredible development in AI.

In this article, the author proposed instances where Artificial Neural Networks are SUPERINTELLIGENT using Jameel’s Criterion.

Proposed Stochastic Superintelligent Artificial Neural Networks

A Deep Learning Neural Networks whose output is Probabilistic is said to be Stochastically Superintelligent:

(1) If all the Hidden Layers’ NEURONS and Output Layer’s NEURONS consists of a combination of only 1st Rated Probabilistic Activation Function satisfies Jameel’s ANNAF Stochastic Criterion, and or;

(2) Depending on the Network’s Number of Neurons, for instance, THREE (3) and SIX (6) NEURONS, if all the Hidden Layers’ NEURONS and Output Layer’s NEURONS consists of a combination of only {1ST, 2ND, 3RD} and {1ST, 2ND, 3RD,…,6TH} Rated Probabilistic Activation Function respectively satisfies Jameel’s ANNAF Stochastic Criterion, and or;

(3) For instance, the N-NEURONS Network system, if all the Hidden Layers’ NEURONS and Output Layer’s NEURONS consists of a combination of only {1ST, 2ND, 3RD,…,nTH}Rated Probabilistic Activation Function respectively satisfies Jameel’s ANNAF Stochastic Criterion. NOTE that this is regardless of NEURONS’ ORDER and OUTPUT LAYERS in the Network systems. These can be shown in the diagrams below:

(1) Proposed One-neuron Stochastic Superintelligent Neural Network

(2) Proposed Three-neurons Stochastic Superintelligent Neural Network

(3) Proposed Six-neurons Stochastic Superintelligent Neural Network

(4) Proposed n- Neurons Stochastic Superintelligent Neural Network

Proposed Deterministic Superintelligent Artificial Neural Networks

A Deep Learning Neural Networks whose output is Deterministic is said to be Deterministically Superintelligent:

(4) If all the Hidden Layers’ NEURONS and Output Layer’s NEURONS consists of a combination of only 1st Rated Deterministic Activation Function satisfies Jameel’s ANNAF Deterministic Criterion, and or;

(5) Depending on the Network’s Number of Neurons, for instance, THREE (3) and SIX (6) NEURONS, if all the Hidden Layers’ NEURONS and Output Layer’s NEURONS consists of a combination of only {1ST, 2ND, 3RD} and {1ST, 2ND, 3RD,…,6TH} Rated Deterministic Activation Function respectively satisfies Jameel’s ANNAF Deterministic Criterion, and or;

(6) For instance, the N-NEURONS Network system, if all the Hidden Layers’ NEURONS and Output Layer’s NEURONS consists of a combination of only {1ST, 2ND, 3RD,…,nTH}Rated Deterministic Activation Function respectively satisfies Jameel’s ANNAF Deterministic Criterion. NOTE that this is regardless of NEURONS’ ORDER and OUTPUT LAYERS in the Network systems. These can be shown in the diagrams below:

(4) Proposed One-neuron Deterministic Superintelligent Neural Network

(5) Proposed Three-neurons Deterministic Superintelligent Neural Network

(6) Proposed Six-neurons Deterministic Superintelligent Neural Network

(7) Proposed n-neurons Deterministic Superintelligent Neural Network

Proposed One-neuron Probabilistic-Deterministic Superintelligent Artificial Neural Networks

A Deep Learning Neural Networks whose output is 1st Rated Probabilistic-Deterministic is said to be Stochastically-Deterministically Super-intelligent if all the Hidden Layers’ NEURONS and Output Layer’s NEURONS are a combination of the only 1st Rated Stochastic and 1st Rated Deterministic Activation Functions satisfies Jameel’s ANNAF Stochastic Criterion and Jameel’s ANNAF Deterministic Criterion as shown below:

Proposed N-NEURONS Probabilistic-Deterministic Superintelligent Artificial Neural Networks

A Deep Learning Neural Networks whose output is Probabilistic-Deterministic is said to be 1st Rated Stochastically-Deterministically Super-intelligent if all the Hidden Layers’ NEURONS and Output Layer’s NEURONS are a combination of 1st, 2nd,…, nth neurons Rated Stochastic and or 1st, 2nd,…, nth neurons Rated Deterministic Activation Functions satisfies Jameel’s ANNAF Stochastic Criterion and Jameel’s ANNAF Deterministic Criterion.

Proposed 2nd Rated Probabilistic-Deterministic Superintelligent Artificial Neural Networks

A Deep Learning Neural Networks whose output is 1st Rated Probabilistic-Deterministic is said to be 2nd Rated Stochastically-Deterministically Super-intelligent if all the Hidden Layers’ NEURONS and Output Layer’s NEURONS are a combination of some Top-Rated Stochastic and or Top-Rated Deterministic Activation Functions satisfies Jameel’s ANNAF Stochastic Criterion and Jameel’s ANNAF Deterministic Criterion.

Let ATRSODAF represents: Any Activation Function among Top-Rated Stochastic or Deterministic Activation Functions then we have the following Deep Neural Network:

Proposed Normal Deep Learning Artificial Neural Networks

A Deep Learning Neural Networks whose output is Normal Probabilistic-Deterministic is said to be Stochastically-Deterministically Normal if all the Hidden Layers’ NEURONS and Output Layer’s NEURONS are combination of only Log-normal Rated Stochastic and Normal Rated Deterministic (equivalent rating to that of Lognormal stochastic) Activation Functions satisfies Jameel’s ANNAF Stochastic Criterion and Jameel’s ANNAF Deterministic Criterion as shown below:

NOTE that these diagrams give the foundation of how we can use Activation Functions Emanated from referenced AI-ML-Purified Data Set in Neural networks. However, in real applications, one may decide his/her arrangement or combinations and output Activation Function(s).

The direction of my next article would work towards achieving “SUPER-INTELLIGENT ARTIFICIAL BRAIN” using Jameel’s ANNAF Stochastic CriterionandJameel’s ANNAF Deterministic Criterion.

AUTHOR

Jamilu Auwalu Adamu, FIMC, CMC, FIMS (UK), FICA (in view)

Associate Editor, Risk and Financial Management Journal, USA

Editor, Journal of Economics and Management Sciences, USA

Former Associate Editor, Journal of Risk Model Validation, UK

PEER-REVIEWER, RISK.NET Journals, London

Former, Steering Committee Member, PRMIA Nigeria Chapter

Books Author

Correspondence: Mathematics Programme Building, 118 National Mathematical Centre, Small Sheda, Kwali, 904105, FCT-Abuja, Nigeria. Tel: +2348038679094. E-mail: whitehorseconsult@yahoo.com

References

TABLECURVE 2D SOFTWARE, SYSTAT (2019) available online: https://systatsoftware.com/products/tablecurve-2d/tablecurve-2d-curve-fitting/

Derivative Calculator (2019) available on: https://www.derivative-calculator.net/

Jamilu Auwalu Adamu (2019), Advanced Stochastic Optimization Algorithm for Deep Learning Artificial Neural Networks in Banking and Finance Industries, Risk and Financial Management Journal, USA, Vol 1 No1 (2019), DOI: https://doi.org/10.30560/rfm.v1n1p8 and available online: https://j.ideasspread.org/index.php/rfm/article/view/387

Jamilu Auwalu Adamu (2019), Superintelligent Deep Learning Artificial Neural Networks, accepted for publication in the International Journal of Applied Science, IDEAS SPREAD. INC, USA (https://j.ideasspread.org/index.php/ijas), preprint available on https://www.preprints.org/manuscript/201912.0263/v1 with doi: 10.20944/preprints201912.0263.v1

Jamilu Auwalu Adamu (2019), Advanced Deterministic Optimization Algorithm for Deep Learning Artificial Neural Networks, accepted for publication in the International Journal of Applied Science, IDEAS SPREAD. INC, USA (https://j.ideasspread.org/index.php/ijas)

Jamilu Auwalu Adamu (2019), Deterministic and Stochastic Superintelligent Digital Brains, Distinct Biological Neurons: Distinct Activation Functions implying Distinct Artificial Neurons, preprints available on researchgate.net and academia.edu respectively via https://www.researchgate.net/publication/338170126_Deterministic_and_Stochastic_Superintelligent_Digital_Brains_Distinct_Biological_Neurons_Distinct_Activation_Functions_implying_Distinct_Artificial_Neurons with DOI: 10.13140/RG.2.2.31550.23368 and https://www.academia.edu/41430249/Deterministic_and_Stochastic_Superintelligent_Digital_Brains

Jamilu Auwalu Adamu (2019), Backward Propagation of Artificial Neural Network: First Derivatives of Advanced Optimized Stochastic Activation Functions, preprints available on researchgate.net via https://www.researchgate.net/publication/337907110_Backward_Propagation_of_Artificial_Neural_Network_First_Derivatives_of_Advanced_Optimized_Stochastic_Activation_Functions , DOI: 10.13140/RG.2.2.14004.60803

Jamilu Auwalu Adamu (2015),Banking and Economic Advanced Stressed Probability of Default Models, Asian Journal of Management Sciences, 03(08), 2015, 10–18.

Jamilu A. Adamu (2015), Estimation of Probability of Default using Advanced Stressed Probability of Default Models, Ongoing Ph.D Thesis, Ahmadu Bello University (ABU), Zaria, Nigeria.

Nair et al. (2010), Rectified linear units improve restricted boltzmann machines, ICML’10 Proceedings of the 27th International Conference on International Conference on Machine Learning Pages 807–814, Haifa, Israel — June 21–24, 2010.

Djork-Arne Clevert, Thomas Unterthiner & Sepp Hochreiter (2016), FAST AND ACCURATE DEEP NETWORK LEARNING BY EXPONENTIAL LINEAR UNITS (ELUS), Published as a conference paper at ICLR 2016

Klambauer et al. (2017),Self-Normalizing Neural Networks, Institute of Bioinformatics, Johannes Kepler University Linz, Austria.

Lichman, 2013, UCI machine learning repository, URL http://archive. ics. uci. edu/ml 901

Aman Dureja and Payal Pahwa (2019), Analysis of Non-Linear Activation Functions for Classification Tasks Using Convolutional Neural Networks, Recent Patents on Computer Science Journal, Volume 12 , Issue 3 , 2019, DOI : 10.2174/2213275911666181025143029

Chigozie Enyinna Nwankpa et al. (2018), Activation Functions: Comparison of Trends in Practice and Research for Deep Learning, available online: https://arxiv.org/pdf/1811.03378.pdf

Soufiane Hayou et al. (2019), On the Impact of the Activation Function on Deep Neural Networks Training, available online: https://arxiv.org/pdf/1902.06853.pdf

Schoenholz et al. (2017), DEEP NEURAL NETWORKS AS GAUSSIAN PROCESSES, Published as a conference paper at ICLR 2018, available online: file:///C:/Users/pc/Downloads/Deep_Neural_Networks_as_Gaussian_Processes.pdf

Asman Dureja and Payal Pahwa (2019), Analysis of Non-Linear Activation Functions for Classification Tasks Using Convolutional Neural Networks, Recent Patents on Computer Science, Volume 12 , Issue 3 , 2019, DOI : 10.2174/2213275911666181025143029

Casper Hansen (2019) says “Better optimized neural network; choose the right activation function, and your neural network can perform vastly better”, available online: https://mlfromscratch.com/neural-networks-explained/#/

Artist Hans Hoffman wrote, “The ability to simplify means to eliminate the unnecessary so that the necessary may speak.” available online: https://www.brainyquote.com/quotes/hans_hofmann_107805

Barnaby Black et.at (2016), Complying with IFRS 9 Impairment Calculations for Retail Portfolios, Moody’s Analytics Risk Perspectives, the convergence of Risk, Finance, and Accounting, Volume VII, June, 2016.

Ben Steiner (2019), Model Risk Management for Deep Learning and Alpha Strategies, BNP Paribas Asset Management, Quant Summit 2019

Bellotti T. and Crook J. (2012), Loss Given Default Models Incorporating Macroeconomic Variables for Credit Cards, International Journal of Forecasting, 28(1), 171–182, DOI: 10.1016/j.ijforecast.2010.08.005

Burton G. Malkiel (2009), The Clustering of Extreme Movements: Stock prices and the Weather, Princeton University, AtanuSaha, Alixpartners, Alex Grecu, Huron Consulting Group, CEPS working paper №186 February, 2009.

Chigozie Enyinna Nwankpa et al. (2018), Activation Functions: Comparison of Trends in Practice and Research for Deep Learning, Preprint.

Nassim N. Taleb (2011), The Future has Thicker Tails Past: Model Error as Branching Counterfactuals, presented in Honor of Benoit Mandelbrot’s at his Scientific Memorial, Yale University, April, 2011.

Nassim N. Taleb (2011), A Map and Simple Heuristic to Detect Fragility, Antifragility, and Model Error, First Version, 2011

Nassim N. Taleb (2010), Why Did the Crisis of 2008 Happen, Draft, 3rd Version, August, 2010.

Nassim N. Taleb (2009), Errors, Robustness, and Fourth Quadrant, New York University Polytechnic Institute and Universa Investment, United States, International Journal of Forecasting 25 (2009) 744–759

Nassim N. Taleb (2010), Convexity, Robustness, and Model Error inside the “Black Swan Domain”, Draft Version, September, 2010.

Nassim N. Taleb et al (2009), Risk Externalities and Too bid to Fail, New York University Polytechnic Institute, 11201, New York, United States.

Nassim N. Taleb (2012), The Illusion of Thin — Tails under Aggregation, NYU — Poly, January, 2012

Nassim N. Taleb (2007), Black Swans and the Domains of Statistics, American Statistician, August 2007, Vol. 6I, №3.

Soufiane Hayou et al. (2019), On the Impact of the Activation Function on Deep Neural Networks Training, Proceedings of the 36 th International Conference on Machine Learning, Long Beach, California, PMLR 97, 2019

TidarukAreerak (2014), Mathematical Model of Stock Prices via a Fractional Brownian Motion Model with Adaptive Parameters

Ton Dieker (2004), Simulation of Fractional Brownian Motion, Thesis, University of Twente, Department of Mathematical Sciences, P.O. BOX 217, 7500 AE Enschede, Netherlands

Wenyu Zhang (2015), Introduction to Ito’s Lemma, Lecture Note, Cornell University, Department of Statistical Sciences, May 6, 2015.

https://www.stoodnt.com/blog/scopes-of-machine-learning-and-artificial-intelligence-in-banking-financial-services-ml-ai-the-future-of-fintechs/

https://medium.com/datadriveninvestor/neural-networks-activation-functions-e371202b56ff

https://missinglink.ai/guides/neural-network-concepts/7-types-neural-network-activation-functions-right/

http://www.datastuff.tech/machine-learning/why-do-neural-networks-need-an-activation-function/

https://medium.com/the-theory-of-everything/understanding-activation-functions-in-neural-networks-9491262884e0

https://www.youthkiawaaz.com/2019/07/future-of-artificial-intelligence-in-banks/

https://news.efinancialcareers.com/uk-en/328299/ai-in-trading-buy-side

https://ai.stackexchange.com/questions/7609/is-nassim-taleb-right-about-ai-not-being-able-to-accurately-predict-certain-type/7610

https://towardsdatascience.com/adam-latest-trends-in-deep-learning-optimization-6be9a291375c

The U.S. Hearing Youtube (Technology Companies & Algorithms): https://www.youtube.com/watch?v=vtw4e68CkwU

https://www.commerce.senate.gov/2019/6/optimizing-for-engagement-understanding-the-use-of-persuasive-technology-on-internet-platforms

https://ai.stackexchange.com/questions/7088/how-to-choose-an-activation-function

https://mlfromscratch.com/activation-functions-explained/#/

https://github.com/nadavo/mood.

Backward propagation and Activation Functions:

https://www.youtube.com/watch?v=q555kfIFUCM

https://www.youtube.com/watch?v=-7scQpJT7uo

https://towardsdatascience.com/analyzing-different-types-of-activation-functions-in-neural-networks-which-one-to-prefer-e11649256209

http://vision.stanford.edu/teaching/cs231n-demos/linear-classify/

http://vision.stanford.edu/teaching/cs231n-demos/knn/

https://playground.tensorflow.org/#activation=tanh&batchSize=10&dataset=circle&regDataset=reg-plane&learningRate=0.03&regularizationRate=0&noise=0&networkShape=4,2&seed=0.41357&showTestData=false&discretize=false&percTrainData=50&x=true&y=true&xTimesY=false&xSquared=false&ySquared=false&cosX=false&sinX=false&cosY=false&sinY=false&collectStats=false&problem=classification&initZero=false&hideText=false