Neural Networks With Disabilities: An Introduction to Complementary Artificial Intelligence

Abstract Machine learning is a good tool to simulate human cognitive skills as it is about mapping perceived information to various labels or action choices, aiming at optimal behavior policies for a human or an artificial agent operating in the environment. Regarding autonomous systems, objects and situations are perceived by some receptors as divided between sensors. Reactions to the input (e.g., actions) are distributed among the particular capability providers or actuators. Cognitive models can be trained as, for example, neural networks. We suggest training such models for cases of potential disabilities. Disability can be either the absence of one or more cognitive sensors or actuators at different levels of cognitive model. We adapt several neural network architectures to simulate various cognitive disabilities. The idea has been triggered by the “coolability” (enhanced capability) paradox, according to which a person with some disability can be more efficient in using other capabilities. Therefore, an autonomous system (human or artificial) pretrained with simulated disabilities will be more efficient when acting in adversarial conditions. We consider these coolabilities as complementary artificial intelligence and argue on the usefulness if this concept for various applications.

[1]  Vagan Terziyan,et al.  Semantics of Voids within Data: Ignorance-Aware Machine Learning , 2021, ISPRS Int. J. Geo Inf..

[2]  Ole Winther,et al.  A Quantitative Study Of Pruning By Optimal Brain Damage , 1993, Int. J. Neural Syst..

[3]  Michael I. Jordan,et al.  Deep Transfer Learning with Joint Adaptation Networks , 2016, ICML.

[4]  David Nordfors,et al.  Coolabilities API , 2018, 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA).

[5]  Richard C. Gerum,et al.  Sparsity through evolutionary pruning prevents neuronal networks from overfitting , 2019, Neural Networks.

[6]  K. Selçuk Candan,et al.  iSparse: Output Informed Sparsification of Neural Network , 2020, ICMR.

[7]  David Nordfors,et al.  A new labor market for people with 'coolabilities' , 2019, Commun. ACM.

[8]  Zenghui Wang,et al.  Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review , 2017, Neural Computation.

[9]  Gary G. Yen,et al.  Pruning Deep Convolutional Neural Networks Architectures with Evolution Strategy , 2021, Inf. Sci..

[10]  Jonathan Bartlett,et al.  Generalized Information: A Straightforward Method for Judging Machine Learning Models , 2019 .

[11]  Kui Ren,et al.  Adversarial Attacks and Defenses in Deep Learning , 2020, Engineering.

[12]  E. Hildt.  Artificial Intelligence: Does Consciousness Matter? , 2019, Front. Psychol..

[13]  Bo Zong,et al.  Learning to Drop: Robust Graph Neural Network via Topological Denoising , 2020, WSDM.

[14]  C. Brainerd.  Deep memory distortions , 2021, Cognitive Psychology.

[15]  Michael Carbin,et al.  The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks , 2018, ICLR.

[16]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[17]  Paul M. Mather,et al.  ASSESSING ARTIFICIAL NEURAL NETWORK PRUNING ALGORITHMS , 2000 .

[18]  Tuure Tuunanen,et al.  Towards digital cognitive clones for the decision-makers: adversarial training experiments , 2020, ISM.

[19]  Gilad Yehudai,et al.  Proving the Lottery Ticket Hypothesis: Pruning is All You Need , 2020, ICML.

[20]  V. Terziyan,et al.  Taxonomy of generative adversarial networks for digital immunity of Industry 4.0 systems , 2020, ISM.

[21]  Michelle R Nario-Redmond,et al.  Crip for a Day: The Unintended Negative Consequences of Disability Simulations , 2017, Rehabilitation psychology.

[22]  Hans Henrik Thodberg,et al.  Improving Generalization of Neural Networks Through Pruning , 1991, Int. J. Neural Syst..

[23]  Yann LeCun,et al.  Optimal Brain Damage , 1989, NIPS.

[24]  Vagan Y. Terziyan.  Challenges of the "Global Understanding Environment" Based on Agent Mobility , 2007 .

[25]  Douglas M. Hawkins,et al.  The Problem of Overfitting , 2004, J. Chem. Inf. Model..

[26]  Ruocheng Guo,et al.  Adversarial Attacks and Defenses , 2020, SIGKDD Explor..

[27]  Reza Farivar,et al.  Towards Automated Machine Learning: Evaluation and Comparison of AutoML Approaches and Tools , 2019, 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI).

[28]  Deborah Kartin,et al.  Instilling positive beliefs about disabilities: pilot testing a novel experiential learning activity for rehabilitation students , 2018, Disability and rehabilitation.

[29]  Chunyan Miao,et al.  A Survey of Zero-Shot Learning , 2019, ACM Trans. Intell. Syst. Technol..

[30]  Jeremy Kepner,et al.  Pruned and Structurally Sparse Neural Networks , 2018, 2018 IEEE MIT Undergraduate Research Technology Conference (URTC).

[31]  Terrence J. Sejnowski,et al.  Interpretation of the Precision Matrix and Its Application in Estimating Sparse Brain Connectivity during Sleep Spindles from Human Electrocorticography Recordings , 2017, Neural Computation.

[32]  Gang Zhang,et al.  AutoPruning for Deep Neural Network with Dynamic Channel Masking , 2020, ArXiv.

[33]  Razvan Pascanu,et al.  How to Construct Deep Recurrent Neural Networks , 2013, ICLR.

[34]  Carl E. Rasmussen,et al.  Pruning from Adaptive Regularization , 1994, Neural Computation.

[35]  D. Goodley.  Disability Studies: An Interdisciplinary Introduction , 2010 .

[36]  Yoshua Bengio,et al.  Hierarchical Recurrent Neural Networks for Long-Term Dependencies , 1995, NIPS.

[37]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[38]  Qian Wang,et al.  Recent Advances in Adversarial Training for Adversarial Robustness , 2021, IJCAI.

[39]  Albert Rizzo,et al.  Virtual Reality as a Tool for Delivering PTSD Exposure Therapy and Stress Resilience Training , 2013 .

[40]  Guotian Xie.  Redundancy-Aware Pruning of Convolutional Neural Networks , 2020, Neural Computation.

[41]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[42]  Elizabeth Barnes.  The Minority Body: A Theory of Disability , 2016 .

[43]  Zachary Chase Lipton.  A Critical Review of Recurrent Neural Networks for Sequence Learning , 2015, ArXiv.

[44]  C. Gill.  Disability, Constructed Vulnerability, and Socially Conscious Palliative Care , 2006, Journal of palliative care.

[45]  Marc'Aurelio Ranzato,et al.  DeViSE: A Deep Visual-Semantic Embedding Model , 2013, NIPS.

[46]  R. Tibshirani,et al.  LassoNet: A Neural Network with Feature Sparsity , 2019, J. Mach. Learn. Res..

[47]  WangWei,et al.  A Survey of Zero-Shot Learning , 2019 .

[48]  Paul R. Daugherty,et al.  Collaborative Intelligence: Humans and AI Are Joining Forces , 2018 .

[49]  Mehdi Khamassi,et al.  Toward Self-Aware Robots , 2018, Front. Robot. AI.

[50]  Tim C. Kietzmann,et al.  Deepfakes: Trick or treat? , 2020, Business Horizons.

[51]  恵子 紀国谷.  国際生活機能分類(International Classification of Functioning, Disability and Health: ICF)にみた福祉・保健・医療の専門職協働における連携に関する貢献と課題 , 2007 .

[52]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[53]  Babak Hassibi,et al.  Second Order Derivatives for Network Pruning: Optimal Brain Surgeon , 1992, NIPS.

[54]  S. Dehaene,et al.  What is consciousness, and could machines have it? , 2017, Science.

[55]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[56]  Hyun Kwon,et al.  Diversity Adversarial Training against Adversarial Attack on Deep Neural Networks , 2021, Symmetry.

[57]  Suyog Gupta,et al.  To prune, or not to prune: exploring the efficacy of pruning for model compression , 2017, ICLR.

[58]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[59]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[60]  Kaiyong Zhao,et al.  AutoML: A Survey of the State-of-the-Art , 2019, Knowl. Based Syst..

[61]  V. Terziyan,et al.  Industry 4.0 Intelligence under Attack : From Cognitive Hack to Data Poisoning , 2018 .