01 Introduction to Machine Learning

01 Introduction to Machine Learning

• 1.
  Neural Networks and FuzzySystems Introduction to Machine Learning 1 Dr. Tamer Ahmed Farrag Electrical Engineering Department Taif University Course No.: 803522-3
• 2.
  Course Outline Part I: Neural Networks (11 weeks) • Introduction to Machine Learning • Fundamental Concepts of Artificial Neural Networks (ANN) • Single layer Perception Classifier • Multi-layer Feed forward Networks • Single layer FeedBack Networks • Unsupervised learning Part II : Fuzzy Systems (4 weeks) • Fuzzy set theory • Fuzzy Systems 2
• 3.
  Introduction to ArtificialIntelligence Systems • Intelligence • Characteristics associated with intelligence in human behavior • Tasks related to intelligence • Learning • Intuition • Creativity • Inference 3
• 4.
  Machine Learning Problemsand Learning Techniques 4 Learning Problems Learning Techniques Machine Learning Supervised Learning Classification Regression Unsupervised Learning Clustering Reinforcement Learning Clustering
• 5.
  Learning Methods Supervised Learning Compare computed output tocorrect output Change network parameters accordingly Unsupervised Learning Correct output is unknown Adapt to structural features of input patterns Reinforced Learning Can only tell if output is incorrect Learn by making mistakes 5
• 6.
  Supervised Learning 6https://www.simplilearn.com/what-is-machine-learning-and-why-it-matters-article • Thetraining process required to make predictions and is corrected when those predictions are wrong. • The training process continues until the model achieves a desired level of accuracy on the training data. • Example problems are classification and regression. • Example algorithms include Logistic Regression and the Back Propagation Neural Network.
• 7.
  Unsupervised Learning 7https://www.simplilearn.com/what-is-machine-learning-and-why-it-matters-article • Amodel is prepared by deducing structures present in the input data. This may be to extract general rules. It may be through a mathematical process to systematically reduce redundancy, or it may be to organize data by similarity. • Example problems are clustering, dimensionality reduction and association rule learning. • Example algorithms include: the Apriori algorithm and k-Means.
• 8.
  Reinforcement Learning (semi-supervised learning) 8https://www.simplilearn.com/what-is-machine-learning-and-why-it-matters-article
• 9.
  Types of MachineLearning Models (problems and tasks) 9 Classification • A classification problem is a problem where we are using data to predict which category something falls into. • we are trying to use data to make a prediction about a discrete set of values or categorizes. • An example of a classification problem could be analyzing a image to determine if it contains a car or a person. • It uses supervised learning methods. Regression (Prediction) • Regression problems are problems where we try to make a prediction on a continuous scale. • Examples could be predicting the stock price of a company or predicting the temperature tomorrow based on historical data. • It uses supervised learning methods. Clustering (Grouping) • Clustering is a process of grouping the data into classes and clusters where the objects reside inside a cluster will have high similarity • The main target of clustering is to divide the whole data into multiple clusters. • Unlike classification process, here the class labels of objects are not known before, • It using unsupervised learning methods.
• 10.
  Sample of MachineLearning Technologies • Neural Networks • Learn the relationship between input and output by example. • Fuzzy Logic • Use probability to represent uncertain facts and apply logical reasoning to partial truths. • Genetic Algorithms • Evolve a solution by repeatedly mixing possible solutions and selecting the solution that leads to the best results. • Expert Systems • Use a pre-existing knowledge base to evaluate input and make informed decisions. • Probabilistic Reasoning • Use statistics to make decisions or predict an outcome. 10
• 11.
  Machine Learning vsDeep Learning 11