Chapter 1.ppt
- 1. 1 INTRODUCTION TO MACHINE LEARNING “Machine Learning” by Anuradha Srinivasaraghavan & Vincy Joseph Copyright 2019 Wiley India Pvt. Ltd. All rights reserved.
- 2. 1. What is Machine Learning? 2. Where is Machine Learning used? 3. Applications of Machine Learning 4. Types of Machine Learning 1. Supervised Learning 2. Unsupervised Learning 3. Reinforcement Learning “Machine Learning” by Anuradha Srinivasaraghavan & Vincy Joseph Copyright 2019 Wiley India Pvt. Ltd. All rights reserved.
- 3. “A computer program is said to learn from experience (E) with respect to some class of tasks (T) and performance measure (P), if its performance at tasks in T, as measured by P, improves with experience E.” –Tom Mitchell Robot Navigation in a MAZE 1. Class of task: Reaching the end of the maze. 2. Performance measurement: Time taken to reach the end of the maze. 3. Source of experience: Navigating the maze from start to finish by the robot. “Machine Learning” by Anuradha Srinivasaraghavan & Vincy Joseph Copyright 2019 Wiley India Pvt. Ltd. All rights reserved.
- 4. ML represents a key evolution in the fields of computer science, data analysis, software engineering and artificial intelligence. Used in Google search engines Facial recognition technologies Recommendation engines Self-driving cars “Machine Learning” by Anuradha Srinivasaraghavan & Vincy Joseph Copyright 2019 Wiley India Pvt. Ltd. All rights reserved.
- 5. Marketing and sales ◦ Uses algorithms interpret diverse datasets and build correlations. ◦ Optimize buyers expectations Search Engines ◦ Personalized match for queries ◦ Google-RankBrain Transportation ◦ Helps in traffic free navigation ◦ Used by Uber and Swiggy “Machine Learning” by Anuradha Srinivasaraghavan & Vincy Joseph Copyright 2019 Wiley India Pvt. Ltd. All rights reserved.
- 6. Supervised: the computer is provided with example inputs that are labeled with their desired outputs Unsupervised: the data is unlabeled, so the learning algorithm is left to find commonalities among its input data. Reinforcement: Concerned with how software agents ought to take action in an environment so as to maximize some notion of cumulative reward. “Machine Learning” by Anuradha Srinivasaraghavan & Vincy Joseph Copyright 2019 Wiley India Pvt. Ltd. All rights reserved.