techprolog

Menu
Menu

Machine learning

4.7 (253 user ratings)
Rated 4.7 out of 5
Specialization
Key Features
Videos

About Specialization:

Machine Learning

Machine learning is a subset of artificial intelligence (AI) that focuses on the development of algorithms and statistical models that enable computers to perform tasks without being explicitly programmed for those tasks. In essence, machine learning algorithms allow computers to learn from data and improve their performance over time. There are several types of machine learning approaches: Supervised Learning, Unsupervised Learning, Reinforcement Learning. Machine learning algorithms can be further categorized based on their learning style: Batch Learning. Online Learning, Semi-Supervised Learning

Key Features/Course content

Videos

  1. Introduction:
    1. Well-posed learning problems
    2. Designing a learning system
    3. Perspectives and issues in
      machine learning
  2. Concept learning and the general to specific ordering:
    1.  Introduction
    2. A concept learning task
    3. Concept
      learning as search
    4. find-S: finding a maximally specific hypothesis
    5. Version Spaces and the candidate
      elimination algorithm
    6. Remarks on version spaces and candidate elimination
    7. Inductive bias
  3. Decision Tree Learning:
    1. Introduction
    2. Decision tree representation
    3. Appropriate problems for decision
      tree learning
    4. The basic decision tree learning algorithm
    5. Hypothesis space search in decision tree
      learning
    6. Inductive bias in decision tree learning
    7. Issues in decision tree learning
  1. Artificial Neural Networks - I:
    1. Introduction
    2. Neural Network representation
    3. Appropriate problems for
      Neural Network learning
    4. Perceptions
    5. Multilayer networks and the Back-Propagation algorithm
  2. Artificial Neural Networks - II:
    1. Remarks on the Back-Propagation algorithm
    2. An illustrative example:
      face recognition
    3. Advanced topics in Artificial Neural Networks
  3. Evaluation Hypotheses: 
    1. Motivation, estimation hypothesis accuracy
    2. Basics of sampling theory
    3. A
      general approach for deriving confidence intervals
    4. Difference in error of two hypotheses
    5. Comparing
      learning algorithms
  1. Bayesian learning
    1. Introduction
    2. Bayes theorem
    3. Bayes theorem and concept learning
    4. Maximum
      Likelihood and least squared error hypotheses
    5. Maximum likelihood hypotheses for predicting
      probabilities
    6. Minimum description length principle
    7. Bayes optimal classifier
    8. Gibs algorithm
    9. Naïve Bayes classifier:
      1. An example: learning to classify text
    10. Bayesian belief networks
    11. The EM algorithm
  2. Computational learning theory
    1. Introduction
    2. Probably learning an approximately correct hypothesis
    3. Sample complexity for finite hypothesis space
    4. Sample complexity for infinite hypothesis spaces
    5. The
      mistake bound model of learning
  3. Instance-Based Learning
    1.  Introduction
    2. k-nearest neighbour algorithm
    3. Locally weighted regression
    4. Radial basis functions
    5. Case-based reasoning
    6. Remarks on lazy and eager learning
  1. Genetic Algorithms:
    1. Motivation, Genetic algorithms
    2. An illustrative example
    3. Hypothesis space search
    4. Genetic programming
    5. Models of evolution and learning
    6. Parallelizing genetic algorithms
  2. Learning Sets of Rules:
    1. Introduction
    2. Sequential covering algorithms
      1. Learning rule sets:
      2. Summary
      3. Learning First-Order rules
        1. Learning sets of First-Order rules:
          1. FOIL
          2. Induction as inverted deduction
          3. Inverting resolution
  3. Reinforcement Learning:
    1. Introduction - The learning task
    2. Q–learning
    3. Non-deterministic
    4. Rewards and actions
    5. Temporal difference learning
    6. Generalizing from examples
    7. Relationship to dynamic programming
    1. Analytical Learning - I:
      1. Introduction
      2. Learning with perfect domain theories:
        1. PROLOG-EBG
        2. Remarks on explanation-based learning
        3. Explanation-based learning of search control knowledge
  2. Analytical Learning - II:
    1. Using prior knowledge to alter the search objective
    2. Using prior knowledge to augment search operators
  3. Combining Inductive and Analytical Learning:
    1. Motivation
    2. Inductive-analytical approaches to
      learning
    3. Using prior knowledge to initialize the hypothesis.
Scroll to Top