Machine Learning Fundamentals PDF

Chapter 1: Beginning with Machine Learning Introduction to Machine Learning Machine learning is used by search engines such as Google and Bing to rank web pages. It is used by social networks such as Facebook and Instagram to generate a custom feed for every user. Email providers such as Gma...

Chapter 1: Beginning with Machine Learning Introduction to Machine Learning Machine learning is used by search engines such as Google and Bing to rank web pages. It is used by social networks such as Facebook and Instagram to generate a custom feed for every user. Email providers such as Gmail,Yahoo, and Hotmail use machine learning to decide which emails are spam and which are not. Introduction to Machine Learning The ultimate aim of machine learning is to build an Artificial Intelligence (AI) platform that is as intelligent as the human mind. We are not very far from this dream and many AI researchers believe that this goal can be achieved through machine learning algorithms that try to mimic the learning processes of a human brain. Applications of Machine Learning Virtual Personal Assistants Traffic Predictions Online Transport Networks Video Surveillance Some media services Email spam and malware filtering Applications of Machine Learning Online customer support Medicine Handwriting recognition Machine Translation Computational Biology and many more. Driverless cars and autonomous helicopters  Defining Machine Learning Definition # 1 Arthur Samuel (1959) coined the term machine learning and defined it as: ‘the field of study that gives computers the ability to learn without being explicitly programmed.’ This is an informal and old definition of machine learning.. Definition # 2 In 1998, Tom Mitchell redefined the concept of machine learning as ‘[A] computer program is said to learn from experience E with respect to some class of tasks T and performance measures P; if its performance at tasks in T, as measured by P, improves with experience E.’ Classification of ML Algorithms. Figure 1.1 : Various types of ML algorithms Supervised learning Supervised learning problems are categorized into either ‘classification’ or ‘regression’ problems. In a regression problem, we try to predict the results within a continuous output.This means that we try to map input variables to some continuous function. In a classification problem instead, we try to predict results in a discrete output. In other words, we try to map input variables into discrete classes or categories. Supervised learning Example The prediction of marks of a student is a case of regression while prediction about his grades or division is classification. The prediction of a score in a cricket match is an example of regression while to predict if the team will win or lose the match is an example of classification. Supervised learning In supervised machine learning, the term "supervised" signifies the fact that the dataset with the "right answers" is given to the algorithm. In simple words, data is labeled. In a regression problem, the system predicts a continuous-valued output (here, it is the price of the house). Supervised learning Let's take another example of supervised learning. Suppose a doctor looks at a dataset of medical records and try to find out whether a breast cancer is benign or malignant. A benign tumor is a harmless tumor and a malignant tumor is a tumor that is dangerous and harmful.F.1.4  Dataset for Diagnosis of Breast Cancer Input Output or Class Attributes Attribute Tumour Size Age mean_perimeter mean_area mean_smoothness diagnosis I 17.99 36 122.8 1001 0.1184 0 n Label 20.57 30 132.9 1326 0.08474 0 s Data 19.69 45 130 1203 0.1096 0 t 14.68 67 94.74 684.5 0.09867 0 a 16.13 65 108.1 798.8 0.117 0 n 19.81 23 130 1260 0.09831 0 c e 13.54 78 87.46 566.3 0.09779 1 s 13.08 86 85.63 520 0.1075 1 9.504 20 60.34 273.9 0.1024 1 Dataset for Diagnosis of Breast Cancer Input Output or Class Attribute Attribute Tumour Size diagnosis I 17.99 0 n 20.57 0 s 19.69 0 t 14.68 0 a 16.13 0 n 19.81 0 c 13.54 1 e 13.08 1 s 9.504 1 Prediction of Tumour as Malignant and Benign Prediction of Tumour as Malignant and Benign Prediction of Tumour as Malignant and Benign Input Output or Class Attributes Attribute Tumour Size Age diagnosis 17.99 36 0 I 20.57 30 0 n 19.69 45 0 s t 14.68 67 0 a 16.13 65 0 n 19.81 23 0 c 13.54 78 1 e 13.08 86 1 s 9.504 20 1 Prediction of Tumour as Malignant and Benign: Adding more features Prediction of Tumour as Malignant and Benign: Adding more features  Prediction of Tumour as Malignant and Benign: Adding more features Input Output or Class Attributes Attribute Tumour Size Age mean_perimeter mean_area mean_smoothness diagnosis I 17.99 36 122.8 1001 0.1184 0 n 20.57 30 132.9 1326 0.08474 0 s 19.69 45 130 1203 0.1096 0 t 14.68 67 94.74 684.5 0.09867 0 a 16.13 65 108.1 798.8 0.117 0 n 19.81 23 130 1260 0.09831 0 c e 13.54 78 87.46 566.3 0.09779 1 s 13.08 86 85.63 520 0.1075 1 9.504 20 60.34 273.9 0.1024 1 Unsupervised learning In unsupervised learning data is not labeled, it means that there is no output attribute. We only have input attributes and on the basis of values of input attributes grouping or clustering is performed on the input data to group them into similar classes. Unsupervised learning Learning of Adam and Eve When Adam and Eve first time reached on earth, then things had their no name. Adam and Eve might have learned by analyzing the attributes or features of the various objects. They might have made the groups or clusters of items based on their features like animate or non-animate, color, shape, size, smell, taste etc. First, they might have categorized the things into living and nonliving groups. Learning of Modern day child On the other hand, in today's world, when a child is born in a family, then his learning is different from Adam and Eve's learning process because now everything is labeled i.e. it has its own name. We show different items to a child and tell the child item's name like a pen, pencil, chair, table, car, bus and so on. Learning evolve with time Unsupervised Supervised Learning Learning Examples of Unsupervised learning Google news as depicted in the Figure is an excellent example of clustering that uses unsupervised learning to group news items based on their contents. Unsupervised learning Reinforcement Learning Reinforcement learning is used in applications like computer games (where the machine plays with a human), driverless cars, robot navigation, etc. It works through trial and error, and the machine selects those actions that yield the greatest rewards. Reinforcement Learning Reinforcement Learning Reinforcement learning is used in applications like computer games (where the machine plays with a human), driverless cars, robot navigation, etc. It works through trial and error, and the machine selects those actions that yield the greatest rewards.These algorithms have three major components mentioned as follows. Agent: It is used for learning and decision making.The agent chooses actions that maximize some specified reward metric over a given amount of time. Environment: It defines the outer world with which the agent interacts. Actions: It defines the tasks to be performed by the agent. Reinforcement Learning Example: The self-driving car from Tesla Motors and Amazon’s prime air delivery are all based on reinforcement learning.  Thanks Happy Learning.