IEEE Symposium on Foundations of Computational Intelligence (IEEE FOCI)

Scope

The 2021 IEEE Symposium on Foundations of Computational Intelligence (FOCI’ 2021) will take place as part of the IEEE Symposium Series on Computational Intelligence (SSCI 2021).

Computational intelligence techniques are widely used to tackle real-world problems due to their numerous successful applications. However, the reasons behind these successes are often not well understood. A solid theoretical foundation of computational intelligence techniques explains the reasons behind the success of these methods. Furthermore, theoretical analyses lead to the understanding of which problems are solved efficiently by a given technique and which are not. Amongst the benefits to practitioners a solid theoretical understanding (a) provides guidance on the choice of the best technique for the problem at hand, (b) helps to identify optimal parameter settings and ultimately (c) aids the design of more effective techniques.

IEEE FOCI’21 will focus on fundamental theoretical foundations of (but not limited to) the three main branches of computational intelligence, Neural Networks and other machine learning methods, Fuzzy Logic and Evolutionary Computation. Although the symposium’s main interest is in theoretical foundations, computational studies of a foundational nature are also welcome. As in the previous SSCI editions, accepted papers will be included in the Conference Proceedings Citation Index.

IEEE FOCI’21, provides an ideal forum for those who are interested in the foundational issues of computational intelligence to exchange their ideas and present their latest findings. Participants of FOCI’21 will also benefit from the interaction at one location with the participants of the several other symposia running concurrently at IEEE SSCI 2021, each highlighting various aspects of computational intelligence. As a whole, this international event will attract top researchers, practitioners, and students from around the world to discuss the latest advances in the field of computational intelligence.

Topics

Fuzzy Logic

  • Non-standard fuzzy sets
  • Granular computing
  • Computing with words
  • Aggregation/fusion
  • Fuzzy sets and statistics
  • Uncertainty
  • Decision-making
  • General theoretical issues
  • Generalisation in neural, fuzzy and evolutionary learning
  • Fuzzy logic and fuzzy set theory
  • Lattice theory and multi-valued logic
  • Approximate reasoning
  • Type-2 fuzzy logic
  • Rough sets and random sets
  • Fuzzy mathematics
  • Fuzzy measure and integral
  • Possibility theory and imprecise probability

Neural Networks and other machine learning techniques

  • Neural computation
  • Self-organizing maps
  • Recurrent networks
  • Multilayer perceptrons
  • Deep Learning, convolutional neural networks, GANs.
  • Autoencoders
  • Evolutionary neural networks
  • Neural networks for pattern recognition
  • Neural netwoks for prediction and optimization
  • Neural networks for principal component analysis
  • General regression neural networks
  • Neural networks as/and fuzzy systems
  • Radial basis functions
  • Learning theory
  • Reinforcement learning
  • Generalization in neural networks

Evolutionary Computation

  • Theoretical foundations of bio-inspired heuristics
  • Exact and approximation runtime analysis
  • Fixed budget computations
  • Black box complexity
  • Self-adaptation
  • Population dynamics
  • Fitness landscape and problem difficulty analysis
  • No Free Lunch Theorems
  • Statistical approaches for understanding the behaviour of bio-inspired heuristics
  • Computational studies of a foundational nature

All bio-inspired search heuristics will be considered for all problem domains including:

  • Combinatorial and continuous optimization
  • Single-objective and multi-objective optimization
  • Constraint handling
  • Dynamic and stochastic optimization
  • Co-evolution and evolutionary learning

Symposium Chairs

Manuel Ojeda-Aciego
aciego@ctima.uma.es
University of Malaga, Spain
Leonardo Franco
lfranco@lcc.uma.es
University of Florida, USA
Pietro S. Oliveto
p.oliveto@sheffield.ac.uk
The University of Sheffield, UK
Chao Qian
qianc@nju.edu.cn
Nanjing University, China