Key Concepts

Designing advanced decision support systems requires the knowledge of a number of theoretical concepts, which are artificial intelligence, cognitive computing, machine learning and operations research. These concepts provide the underlying theory of our technology.

Artificial Intelligence

Artificial Intelligence (AI) studies the effort of designing computer software that is capable of intelligent behavior with many researchers defining the field as the study and design of intelligent agents. AI is a broad, technical field that focuses on several problems including those relating to reasoning, knowledge, planning, learning, natural language processing, and perception. Learn more

Cognitive Computing

Cognitive computing is the emulation of human thought processes and reasoning. According to Sue Feldman and Hadley Reynolds, the following characteristics define a cognitive computing system:

  • Adaptive
  • Interactive
  • Interative and stateful
  • Contextual

Machine Learning

Machine learning is a subfield of computer science and statistics that gives models the ability to learn without being explicitly programmed. Machine learning algorithms build a model based on data inputs and use that model to make predictions and interpret new data. Some basic algorithms used in machine learning are Naïve Bayes, Nearest Neighbors, Mean Classifier, and Perceptron. The type of algorithms used is often dictated by the type of problem and how the data should be interpreted. Most algorithms fall into four different categories: supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning.

Operations Research

Operations Research (OR) is a discipline that deals with the application of advanced analytical methods to help make better decisions and has close ties with computer science and mathematics. OR encompasses a wide range of problem-solving techniques and methods such as simulation, optimization, queuing theory, Markov processes, data analysis, statistics, and more. By using OR techniques, CSI is able to arrive at optimal or near-optimal solutions to complex decision-making problems.

Intelligent Agents

At CSI, we define an intelligent agent as programs that carry out tasks on behalf of a user, unsupervised and using degree of intelligent reasoning to perform the task in regards to the resources, capabilities, and the situation. These agents are designed using the concepts above and must exhibit all of the following six characteristics:

  • Autonomous
  • Goal Oriented/Taskable
  • Proactive/Persistent
  • Adaptive/Capable of Learning
  • Collaborative/Communicative
  • Distributed & Mobile (optional)