The human brain is complex and digital intelligence is far away from reaching its processing abilities.
Improving artificial intelligence (AI) is driving a lot or research in engineering and neuroscience, and recently, Chris Eliasmith and his team (University of Waterloo in Ontario) published an article on a brain model called “SPAUN” in the journal Science (http://www.sciencemag.org/content/338/6111/1202).
SPAUN stands for “Semantic Pointer Architecture Unified Network”. Continue reading “SPAUN – A Digital Brain More Human Than Ever” »
Critical systems of the government, businesses, health system and financial institutions etc. are continuously challenged by cyber-attacks.
Conventional tactics frequently fail to prevent and fight those attacks because the classic systems are usually run in static environments that easily permit hackers to target and damage system resources.
Traditionally, network parameters such as addresses, names, software applications, networks and numerous configuration parameters remain fairly static over long periods of time. Hackers assume these enterprise networks use these static configurations, which gives hackers opportunities to research the environment and plan attacks against the system. Continue reading “Moving Target Defense Systems: Self-Adapting Computer Networks” »
Genetic Algorithms (GAs) are non-linear adaptive optimization methods that mimic natural evolution processes via non-exhaustive searches among randomly generated solutions. Genetic Algorithms are highly operative for searching through large or complex data structures seeking the optimal solution for decision, classification, optimization and simulation. Continue reading “Genetic Algorithms in Medicine” »
Artificial Neural Networks (ANNs) are one of the “hot” topics in creating innovative medical diagnosis and treatment software for patient-centered medicine.
Neural networks are a class of pattern recognition methods to model the biological neuron to process non-linear or chaotic information where no algorithmic solution is possible or the solution is too complex for traditional techniques.
Recent ANN applications include the modeling of the human body recognizing patterns in scans such as MRI, CAT scans or X-rays but are also used for analyzing brain maturation, ultrasound pictures or cardiograms. They are applied to resolve different diagnostic problems such as detection and classification of cancer, cardiovascular diseases and the processing of EEG signals. Continue reading “Neural Networks IV – Medical Innovation of Tomorrow” »
Artificial neural networks (ANN) imitate the principles of the biological brain and are progressively more applied across research, medical, engineering, social science and other fields. They also deliver substantial benefits in business applications.
Today’s world is multifaceted and there are countless inter-related variables that make predicting business outcomes very difficult. ANNs are the modern computational tools to study data and develop models to identify patterns and structures in data that offer Continue reading “Neuronal Networks in Business and Marketing” »
Both, the learning of human neurons and artificial neural networks (ANNs) occur in a training phase and an operation phase. Feed-forward ANNs are very steady and may range over multiple units without having any feedback connections present whereas recurrent ANNs, that do contain feedback connections and provide dynamic network components, that allow developing a dynamic behavior of output patterns of the neural network.
An ANN learns “off-line” if the learning and operation phases are separate and it learns “on-line” if learning and operating are performed at the same time Continue reading “Artificial Neural Networks – Learning Smart” »
Artificial neural networks (ANNs) are an attempt to simulate the human brain within a computer system.
Both, biological and artificial neuronal networks are built from atomic modules – the ‘neurons’. The human brain has up to 150 billion neurons with hundreds of different classified subtypes. Each neuron usually has one axon, which expands off from a part of the cell body to conduct electrical signals to other cells. Thousands of interconnected neurons build separate groups that are called networks.
Biological neurons can be classified into ‘sensory neurons’ that provide all information for perception and motor coordination, ‘motor neurons’ which transfer signals to muscles and glands and ‘inter-neuronal neurons’ that are needed to relay information, protect other neurons or connect different parts of the brain. These neurons have linear and non-linear relationships to obtain and transfer information as well as to build memory. Continue reading “Neural Networks I – Artificial Neural Networks” »