Scientific Vision
Complex Systems - A systemic Approach
A selection of the scientists and thinkers who inspire us in every day work
The concept of "System" arise already in the ancient Greece, when they approach to the study of the natural phenomena or of the human body. See Ippocrate's Holistic approach to Medicine (460 a. C. – 360 a. C.)
The most famous quote about Complex Systems comes from Aristotle (384 – 322 BC) who said that "The whole is more than the sum of its parts"
The German philosopher Friedrich Hegel (1770 - 1831) characterises general systems as an integrated whole in which:
The whole is more than the sum of the parts
The whole defines the nature of the parts
The parts cannot be understood by studying the whole
The parts are dynamically interrelated or interdependent
Nature is a Complex System
Surrounding Nature is a complex system of systems. Wherever we look, we see systems capable of self-organizing from which order emerges spontaneously thanks to a mysterious intrinsic intelligence. From brain neurons to the flight of birds in flocks, from biological ecosystems to technological ecosystems, from economics to societies, matter and information are organized in complex patterns. Western science and engineering show that it is possible to imitate some aspects of this intelligence through innovative models that take into account the fact that it is not only the elements of the system that are important but also their reciprocal interrelation.
Systemic Thinking
Systems thinking is a holistic approach to analysis that focuses on the way that a system's constituent parts interrelate and how systems work over time and within the context of larger systems. The systems thinking approach contrasts with traditional analysis, which studies systems by breaking them down into their separate elements. Systems thinking can be used in any area of research and has been applied to the study of medical, environmental, political, economic, human resources, and educational systems, among many others.
Chaotic Systems
In the context of science, a chaotic system is defined as one that is highly sensitive to initial conditions. Commonly, the word chaos is used differently. The dictionary defines chaos as “a state of utter confusion or disorder; a total lack of organization or order.” The consequences of the high sensitivity to initial conditions lead to some apparent attributes that are associated with the common usage of the term chaos. However, chaos in the context of science is not random. The process can be approached more systematically. The process can be modeled by mathematical equations and to some extent approached quantitatively. This type of a chaos is often called deterministic chaos.
Complex Systems
Complex Systems are an interdisciplinary field of research that seeks to explain how large numbers of relatively simple entities organize themselves without the benefit of any central controller into a collective whole that creates patterns use information and in some cases evolve and learn. Complex systems are systems whose behavior is intrinsically difficult to model due to the dependencies, competitions, relationships, or other types of interactions between their parts or between a given system and its environment. Systems that are "complex" have distinct properties that arise from these relationships, such as nonlinearity, emergence, spontaneous order, adaptation, and feedback loops, among others.
Complex Systems - Many definitions… but of course:
Complex Collective behavior (elements interact with simple rule without central controller or leader)
Signalling and information processing from both internal and external environments
Adaptation via learning and evolution
Self-organizing, hierarchical organization
Emergence (of functions at a higher level of the system not present in the constituent subsystems)
John Horgan in «From complexity to perplexity», Scientific American, 1995, mentioned 31 different definitions for «complexity»
Complex Systems modeling - Artificial Intelligence
Complex systems have intelligent behavior and, consequently, the modeling and control of such systems require intelligent algorithms and procedures. Furthermore, very often there is no mathematical model to describe the behavior of complex systems and it is necessary to resort to a particular data-based modeling methodology known as data-driven modeling.
Information can be converted into knowledge about historical patterns and future trends
The Rock by T. S. Eliot in 1934
“Where is the Life we have lost in living?
Where is the wisdom we have lost in knowledge?
Where is the knowledge we have lost in information?”
The DIKW pyramid
(Information Management)
Necessary AI capability: Learn, adapt to new situations, generalize, abstract, discover and associate
Computational System Thinking Machines (CSTMs)
Techniques of Computational Intelligence, Soft Computing, Granular Computing
Intelligent Sensing (ANN-PSO)
Monitor and Identification;
Forecasting (ANN-Neurofuzzy)
Scheduling (ANN –Fuzzy System)
Intelligent Control
Intelligent/Adaptive Relay
Intelligent Fault recognition
Computational Intelligence
The expression computational intelligence (CI) usually refers to the ability of a computer to learn a specific task from data or experimental observation. Even though it is commonly considered a synonym of soft computing, there is still no commonly accepted definition of computational intelligence. Generally, computational intelligence is a set of nature-inspired computational methodologies and approaches to address complex real-world problems to which mathematical or traditional modelling can be useless for a few reasons: the processes might be too complex for mathematical reasoning, it might contain some uncertainties during the process, or the process might simply be stochastic in nature.
Pattern recognition
Pattern recognition is the automated recognition of patterns and regularities in data. It has applications in statistical data analysis, signal processing, image analysis, information retrieval, bioinformatics, data compression, computer graphics and machine learning.
Soft Computing
Soft computing is a set of algorithms, including neural networks, fuzzy logic, and genetic algorithms. These algorithms are tolerant of imprecision, uncertainty, partial truth and approximation. It is contrasted with hard computing: algorithms which find provably correct and optimal solutions to problems. The theory and techniques related to soft computing were first introduced in 1980s.The term "soft computing" was coined by Lotfi A. Zadeh.
Granular Computing
Granular computing (GrC) is an emerging computing paradigm of information processing that concerns the processing of complex information entities called "information granules", which arise in the process of data abstraction and derivation of knowledge from information or data. Generally speaking, information granules are collections of entities that usually originate at the numeric level and are arranged together due to their similarity, functional or physical adjacency, indistinguishability, coherency, or the like. Fort our research GrC is not only an algorithmic paradigm but also a way of multidimensional and systemic thinking for synthesizing intelligent procedures and models in complex systems (learn more).
Deep Learning
Clustering
Evolutionary Computation
Fuzzy Logic
The problem of RepresentatioN in Pattern recognition (and also in Cognitive SciencE)
The problem of representation is a core issue for pattern recognition. It encodes the real-world objects by some numerical description, handled by computers in such a way that the individual object representations can be interrelated. Based on that, later a generalization is achieved, establishing descriptions or discriminations between classes of objects. Originally, the issue of representation was almost neglected, as it was reduced to the demand of having good features provided by some experts. The learning is often believed to start at the given feature vector space. Indeed, many books on pattern recognition disregard the topic of representation, simply by assuming that objects are somehow already represented. (Learn More)
Machine Learning with GPU Acceleration
Businesses use machine learning to improve their products, services, and operations. By leveraging large amounts of historical data, businesses can build models to predict customer behaviors and refine internal processes. While machine learning provides incredible value to an enterprise, current CPU-based methods can add complexity and overhead reducing the return on investment for businesses. With a data science acceleration platform that combines optimized hardware and software, the traditional complexities and inefficiencies of machine learning disappear. Data scientists can now conduct rapid feature iteration, use massive datasets for highly accurate predictions, and deliver value-generating solutions to production with ease. Data scientists can easily access GPU-acceleration through some of the most popular Python or Java-based APIs, making it easy to get started fast whether in the cloud or on-premise. By leveraging the power of accelerated machine learning, businesses can empower data scientists with the tools they need to get the most out of their data. (Learn More)
Inspirational Books [English]
Inspirational Books [Italian]
The origin of Artificial Intelligence fascination - Vintage
“Imagination is the real and eternal world of which this vegetable universe is but a faint shadow.” ―William Blake
The hierarchical organization of the universe: The Scale of the Universe
DEEP Learning - Artificial Neural Networks
Artificial Neural Networks are algorithms that mimic functionally the animal brain
Artificial Neural Network firing process
Decision regions creation during learning
In deep learning, a convolutional neural network (CNN, or ConvNet) is a class of Artificial Neural Network(ANN), most commonly applied to analyze visual imagery. (Learn more)
Convolution process
Information flow in CNNS
A graph neural network (GNN) is a class of neural network for processing data best represented by graph data structures. (Learn more)
A recurrent neural network (RNN) is a class of artificial neural networks where connections between nodes form a directed or undirected graph along a temporal sequence. This allows it to exhibit temporal dynamic behavior. (Learn More)
A transformer is a deep learning model that adopts the mechanism of self-attention, differentially weighting the significance of each part of the input data. It is used primarily in the fields of natural language processing (NLP) and computer vision (CV) (Learn more).
property of CIPAR TEAMS © - 2024