CS 5354/CS 4365: Intelligent Computing: Time to Gather Stones

Fall 2019

  • Instructor: Vladik Kreinovich, email vladik@utep.edu, office CCSB 3.0404,
    office phone (915) 747-6951
  • Class time: Mondays and Wednesdays, 3-4:20 pm, CCSB 1.0702
  • Details: Syllabus

Faculty office hours

  • The instructor's office hours are Mondays and Wednesdays 1:30-3 pm and 4:30-5:30 pm, or by appointment.
  • If you want to come during the scheduled office hours, there is no need to schedule an appointment.
  • If you cannot come during the instructor's scheduled office hours, please schedule an appointment in the following way: He will then send a reply email, usually confirming that he is available at this time, and he will place the meeting with you on his schedule.

Homeworks and programming assignments

Quizzes

Resources on Fuzzy Techniques

  • pdf file
  • Vladik Kreinovich, Jonathan Quijas, Esthela Gallardo, Caio De Sa Lopes, Olga Kosheleva, and Shahnaz Shahbazova, "Simple Linear Interpolation Explains All Usual Choices in Fuzzy Techniques: Membership Functions, t-Norms, t-Conorms, and Defuzzification", Proceedings of the Annual Conference of the North American Fuzzy Information Processing Society NAFIPS'2015 and 5th World Conference on Soft Computing, Redmond, Washington, August 17-19, 2015. pdf file

Resources on Neural Networks

  • Vladik Kreinovich, "From Traditional Neural Networks to Deep Learning: Towards Mathematical Foundations of Empirical Successes", In: Shahnaz N. Shahbazova, Janusz Kacprzyk, Valentina Emilia Balas, and Vladik Kreinovich (eds.) Proceedings of the World Conference on Soft Computing, Baku, Azerbaijan, May 29-31, 2018. pdf file
  • Foundations of Deep Learning: Mathematical Details
  • Chitta Baral, Olac Fuentes, and Vladik Kreinovich, "Why Deep Neural Networks: A Possible Theoretical Explanation", In: Martine Ceberio and Vladik Kreinovich (eds.), Constraint Programming and Decision Making: Theory and Applications, Springer Verlag, Berlin, Heidelberg, 2018, pp. 1-6. pdf file
  • Olac Fuentes, Justin Parra, Elizabeth Anthony, and Vladik Kreinovich, "Why Rectified Linear Neurons Are Efficient: A Possible Theoretical Explanations", In: Olga Kosheleva, Sergey Shary, Gang Xiang, and Roman Zapatrin (eds.), Beyond Traditional Probabilistic Data Processing Techniques: Interval, Fuzzy, etc. Methods and Their Applications, Springer, Cham, Switzerland, 2019, to appear. pdf file
  • Olga Kosheleva and Vladik Kreinovich, "Why Deep Learning Methods Use KL Divergence Instead of Least Squares: A Possible Pedagogical Explanation", Mathematical Structures and Modeling, 2018, Vol. 46, pp. 102-106. pdf file
  • Afshin Gholamy, Justin Parra, Vladik Kreinovich, Olac Fuentes, and Elizabeth Anthony, "How to Best Apply Deep Neural Networks in Geosciences: Towards Optimal 'Averaging' in Dropout Training", In: Junzo Watada, Shing Chieng Tan, Pandian Vasant, Eswaran Padmanabhan, and Lakhmi C. Jain (eds.), Smart Unconventional/ Modelling, Simulation and Optimization for Geosciences and Petroleum Engineering, Springer Verlag, 2019, pp. 15-26. pdf file
  • Gerardo Muela, Christian Servin, and Vladik Kreinovich, "How to Make Machine Learning Robust Against Adversarial Inputs", Mathematical Structures and Modeling, 2017, Vol. 42, pp. 127-130. pdf file
  • Vladik Kreinovich and Olga Kosheleva, "Optimization under Uncertainty Explains Empirical Success of Deep Learning Heuristics", Technical Report UTEP-CS-19-49, 2019. pdf file

Resources on Quantum Computing

  • O. Kosheleva and V. Kreinovich, "How to Introduce Technical Details of Quantum Computing in a Theory of Computation Class: Using the Basic Case of the Deutsch-Jozsa Algorithm", International Journal of Computing and Optimization, 2016, Vol. 3, No. 1, pp. 83-91. pdf file
  • Oscar Galindo, Olga Kosheleva, and Vladik Kreinovich, "Towards Parallel Quantum Computing: Standard Quantum Teleportation Algorithm Is, in Some Reasonable Sense, Unique", Proceedings of the 7th International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making IUKM'2019, Nara, Japan, March 26-29, 2019. pdf file
  • Oscar Galindo, Vladik Kreinovich, and Olga Kosheleva, "Current Quantum Cryptography Algorithm Is Optimal: A Proof", Proceedings of the IEEE Symposium on Computational Intelligence for Engineering Solutions CIES'2018, Bengaluru, India, November 18-21, 2018. pdf file
  • Oscar Galindo and Vladik Kreinovich, "For Quantum and Reversible Computing, Intervals Are More Appropriate Than General Sets, and Fuzzy Numbers Than General Fuzzy Sets", Proceedings of the Joint 11th Conference of the European Society for Fuzzy Logic and Technology EUSFLAT'2019 and International Quantum Systems Association (IQSA) Workshop on Quantum Structures, Prague, Czech Republic, September 9-13, 2019. pdf file
  • Oscar Galindo, Laxman Bokati, and Vladik Kreinovich, "Towards a More Efficient Representation of Functions in Quantum and Reversible Computing", Proceedings of the Joint 11th Conference of the European Society for Fuzzy Logic and Technology EUSFLAT'2019 and International Quantum Systems Association (IQSA) Workshop on Quantum Structures, Prague, Czech Republic, September 9-13, 2019. pdf file
  • Christian Ayub, Martine Ceberio, and Vladik Kreinovich, "How Quantum Computing Can Help With (Continuous) Optimization", Proceedings of the 12th International Workshop on Constraint Programming and Decision Making CoProd'2019, Part of the World Congress of the International Fuzzy Systems Association and the Annual Conference of the North-American Fuzzy Information Processing Society IFSA/NAFIPS'2019, Lafayette, Louisiana, June 17, 2019, to appear. pdf file
  • Oscar Galindo, Christian Auyb, Martine Ceberio, and Vladik Kreinovich, "Faster Quantum Alternative to Softmax Selection in Deep Learning and Deep Reinforcement Learning", Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence SSCI'2019, Xiamen, China, December 6-9, 2019, to appear. pdf file
  • Vladik Kreinovich, Martine Ceberio, and Ricardo Alvarez, "How to Use Quantum Computing to Check Which Inputs Are Relevant: A Proof That Deutsch-Jozsa Algorithm Is, In Effect, the Only Possibility", Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence SSCI'2019, Xiamen, China, December 6-9, 2019, to appear. pdf file
  • Olga Kosheleva and Vladik Kreinovich, "Secure Multi-Agent Quantum Communication: Towards the Most Efficient Scheme (A Pedagogical Remark)", Mathematical Structures and Modeling, 2019, Vol. 49, pp. 119-125. pdf file
  • Ricardo Alvarez, Nick Sims, Christian Servin, Martine Ceberio, and Vladik Kreinovich, "If Space-Time Is Discrete, We May Be Able to Solve NP-Hard Problems in Polynomial Time", Technical Report UTEP-CS-19-85, 2019. pdf file

Department of Computer Science | The University of Texas at El Paso