Learning System

A Learning System is a system (that applies a learning algorithm and can solve a learning task (has a learning ability to to improve its system performance based on experience).

• Context:
  • It can range from being a Biological Learning System to being a Mechanical Learning System/Software-based Learning System.
  • It can range from being an Inductive Learning System to being Deductive Learning System.
  • It can make use of a Learning Subsystem (that applies a Learning Algorithm).
  • It can range from being an Unsupervised Learning System, to being a Supervised Learning System, to being a Reinforcement Learning System.
  • It can range from being a Narrow Learning System to being a General Learning System.
  • It can make use of a Belief System.
• Example(s):
  • a Person.
  • a Learning Machine.
  • a Deep Learning System.
  • a Quantum Machine Learning System.
  • a Relational Learning System.
  • a Behavioral Cloning System.
  • a Concept Drift System.
  • a Preference Learning System.
  • a Cost-Sensitive Learning System.
  • a Supervised Learning System such as:
    • a Regression Learning System.
    • a Classification Learning System.
    • a Feed-Forward Neural Network.
  • an Unsupervised Learning System such as:
    • a Clustering System.
    • a Self-Organizing Map.
  • a Reinforcement Learning System such as:
    • a Relational Reinforcement Learning System.
    • a Gaussian Process Reinforcement Learning System.
    • a Bayesian Reinforcement Learning System.
  • an Active Learning System.
  • a Semisupervised Learning System.
  • …
• Counter-Example(s):
  • a Heuristic-based System.
  • a Game Playing System.
  • a Metalearning System.
• See: Learning Algorithm, Learning Task, Reinforcement, Natural Language Processing System, Artificial Intelligence, Inductive Inference, Computational Learning Theory, Learning Curve, Decision Tree, Artificial Neural Network, Logistic Regression, Inductive Inference.

---

---

References

2008

• (Wilson, 2008a) ⇒ Bill Wilson. (2008). “The Machine Learning Dictionary for COMP9414." University of New South Wales, Australia.
  • learning program: Normal programs P produce the same output y each time they receive a particular input x. Learning programs are capable of improving their performance so that they may produce different (better) results on second or later times that they receive the same input x. They achieve this by being able to alter their internal state, q. In effect, they are computing a function of two arguments, P(x | q) = y. When the program is in learning mode, the program computes a new state q' as well as the output y, as it executes. In the case of supervised learning, in order to construct q', one needs a set of inputs [math]\displaystyle{ x_i }[/math] and corresponding target outputs zi (i.e. you want P(xi | q) = zi when learning is complete). The new state function L is computed as: L(P, q, ((x1,z1), ..., (xn, zn))) = q'. See also unsupervised learning, observation language, and hypothesis language.

     machine learning: Machine learning is said to occur in a program that can modify some aspect of itself, often referred to as its state, so that on a subsequent execution with the same input, a different (hopefully better) output is produced. See unsupervised learning and supervised learning, and also function approximation algorithms and symbolic learning algorithms.

---