Download to read offline
INTRODUCTION TO ML basics of ml that one should know
- 1.
- 2. Basic Understanding ofMachine Learning • Traditional Programming: Data and program is run on the computer to produce the output. • Machine Learning: Data and output is run on the computer to create a program. This program can be used in traditional programming. • Machine Learning is an application of artificial intelligence where a computer/machine learns from the past experiences and makes future predictions. • The past experience is developed through the data collected. • In order to perform the task, the system learns from the data-set provided. • A data-set is a collection of many examples. • An example is a collection of features. • Machine Learning refers to the techniques involved in dealing with vast data in the most intelligent fashion (by developing algorithms) to derive actionable insights.
- 3. Basic Understanding ofMachine Learning • 1950 • Samuel developed checker playing program and he coined the term Machine learning • 1960 • Neural Network- Rosenblatt perceptron • Pattern Recognition • Minsky and Papert proved limitation of Perceptron • 1970 • Decision tree – J.R Quinlan • Natural Language processing • 1980 • Advanced decision tree and rule based learning • Resurgence of neural network- Multilayer perceptron and neural network specific back propagation algorithm was developed • PAC- probably approximate correct learning • 1990 ( Machine learning embraced statistics to a large extent) • SVM- 1995 • Data mining • Adaptive agents and web applications • Text learning • Reinforcement learning • Ensembles • Bayes learning Brief History
- 4. Basic Understanding ofMachine Learning
- 5. Basic Understanding ofMachine Learning • Medicine • Diagnose a disease • Input: Symptoms , Lab measurement, test results, DNA tests,…… • Output: one of set of possible disease , or none of the above • Data mine historical medical records to learn which future patients will respond best to which treatment. • Robot control • Design autonomous mobile robots that learn to navigate from their own experience • Financial • Predict if a stock will rise or fall in few millisec • Predict if a user will click on an ad or not in order to decide which ad to show. • Application in Business intelligence • Robustly forecasting product sale quantities taking seasonality and trend into account • Identify price sensitivity of a consumer product and identify the optimum price point that maximizes the net profit. • Some other applications • Fraud detection: Credit card providers determines whether or not someone will default. • Understanding the consumer sentiment based on unstructured text data. • Self customized program • e.g. Amazon, Netflix product recommendation • Algorithm learns by itself to customize. Many domains and application
- 6. Basic Understanding ofMachine Learning • Text Mining • Natural Language Processing • Fault Diagnostics • Load Forecasting • Control and Automation • Business Intelligence • Machine Vision • Biometric Recognition • Handwriting Recognition • Medical Diagnosis • Alignment of Biological Sequences • Drug Design • Speech Recognition • Examples of applications in diverse fields
- 8. Basic Understanding ofMachine Learning • The field of machine learning is concerned with the question of how to construct computer programs that automatically improve with experience. • In recent years many successful machine learning applications have been developed, ranging from data-mining programs that learn to detect fraudulent credit card transactions, to information-filtering systems that learn users' reading preferences, to autonomous vehicles that learn to drive on public highways. • At the same time, there have been important advances in the theory and algorithms that form the foundations of this field. • Machine learning draws on concepts and results from many fields, including statistics, artificial intelligence, philosophy, information theory, biology, cognitive science, computational complexity, and control theory.
- 9. • Artificial Intelligence:It refers to the procedure of programming a computer (machine) to take rational. • to make the machine behave in an excellent fashion in lieu of human guidance. • ML is a subset of AI. • Statistics: utilizes data to carry out the analysis and present inferences. • regression,variance, standard deviation, conditional probability etc. • Machine learning algorithms uses statistical concepts to execute machine learning • Deep Learning: associated with a ML algorithm (ANN) which uses the concept of human brain to facilitate the modeling of arbitrary functions. • ANN requires a vast amount of data and this algorithm is highly flexible when it comes to model multiple outputs simultaneously. • Data Mining: deals with searching specific information • ML solely concentrates on performing a given task Basic Understanding of Machine Learning • How is machine learning different from ____
- 10. Basic Understanding ofMachine Learning • The process of teaching machines can be broken down into 3 parts
- 11. Basic Understanding ofMachine Learning • If we could understand how to program to learn (to improve automatically with experience) the impact would be dramatic. • Imagine computers • learning from medical records which treatments are most effective for new diseases, • houses learning from experience to optimize energy costs based on the particular usage patterns of their occupants, • personal software assistants learning the evolving interests of their users in order to highlight especially relevant stories from the online morning newspaper. • A successful understanding of how to make computers learn would open up many new uses of computers and new levels of competence and customization. • algorithms have been invented that are effective for certain types of learning tasks, and a theoretical understanding of learning is beginning to emerge.
- 12. Basic Understanding ofMachine Learning • Machine learning addresses the question of how to build computer programs that improve their performance at some task through experience. • 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
- 13. Classifying emails asspam or not spam. Watching you label emails as spam or not spam. The number (or fraction) of emails correctly classified as spam/not spam. None of the above—this is not a machine learning problem. Suppose your email program watches which emails you do or do not mark as spam, and based on that learns how to better filter spam. What is the task T in this setting? “A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.” T E P
- 14. Basic Understanding ofMachine Learning • Block diagrammatic representation of a learning machine
- 15. Basic Understanding ofMachine Learning 1. Collecting data: Be it the raw data from excel, access, text files etc., this step (gathering past data) forms the foundation of the future learning. • The better the variety, density and volume of relevant data, better the learning prospects for the machine becomes. 2. Preparing the data: Any analytical process thrives on the quality of the data used. • One needs to spend time determining the quality of data and then taking steps for fixing issues such as missing data and treatment of outliers. 3. Training a model: This step involves choosing the appropriate algorithm and representation of data in the form of the model. • The cleaned data is split into two parts – train and test (proportion depending on the prerequisites); • the first part (training data) is used for developing the model. • The second part (test data), is used as a reference. • Steps used in Machine Learning
- 16. Basic Understanding ofMachine Learning 4. Evaluating the model: To test the accuracy, the second part of the data (holdout / test data) is used. • This step determines the precision in the choice of the algorithm based on the outcome. • A better test to check accuracy of model is to see its performance on data which was not used at all during model build. 5. Improving the performance: This step might involve choosing a different model altogether or introducing more variables to augment the efficiency. • That’s why significant amount of time needs to be spent in data collection and preparation. • Steps used in Machine Learning
- 17. Formulating a MachineLearning Problem and Models: Special Emphasis on Target Function
- 18. • Designing anylearning system includes • Choosing the Training Experience • Choosing the Target Function • Choosing a Representation for the Target Function • Choosing a Function Approximation Algorithm • ESTIMATING TRAINING VALUES • ADJUSTING THE WEIGHTS • The Final Design • Few Other Examples: • Learning to recognize spoken words • Learning to drive an autonomous vehicle • Learning to classify new astronomical structures • Learning to play world-class backgammon • Summary of choices in designing the checkers learning program A checkers learning problem:
- 19. A checkers learningproblem: • A checkers learning problem: • Task T: playing checkers • Performance measure P: percent of games won against opponents • Training experience E: playing practice games against itself • In order to complete the design of the learning system, we must now choose • the exact type of knowledge to be learned • a representation for this target knowledge • a learning mechanism • Summary of choices in designing the checkers learning program
- 20. Designing a programto learn to play checkers Choosing the Training Experience: • The system might learn from direct training examples consisting of individual checkers board states and the correct move for each. • Alternatively, it might have available only indirect information consisting of the move sequences and final outcomes of various games played. • In this later case, information about the correctness of specific moves early in the game must be inferred indirectly from the fact that the game was eventually won or lost. • Due to Credit assignment problem, learning from direct training feedback is typically easier than learning from indirect feedback.
- 21. Designing a programto learn to play checkers Choosing the Training Experience: • A second important attribute of the training experience is the degree to which the learner controls the sequence of training examples. • A third important attribute of the training experience is how well it represents the distribution of examples over which the final system performance P must be measured. • To proceed with our design, let us decide that our system will train by playing games against itself. • This has the advantage that no external trainer need be present, and it therefore allows the system to generate as much training data as time permits.
- 22. Designing a programto learn to play checkers Choosing the Target Function: • The next design choice is to determine exactly what type of knowledge will be learned and how this will be used by the performance program. • Let us begin with a checkers-playing program that can generate the legal moves from any board state. • The program needs only to learn how to choose the best move from among these legal moves. • This learning task is representative of a large class of tasks for which the legal moves that define some large search space are known a priori, but for which the best search strategy is not known.
- 23. Designing a programto learn to play checkers • Choosing the Target Function: • The most obvious choice for the type of information to be learned is a program, or function, that chooses the best move for any given board state. • Another choice is an evaluation function that assigns a numerical score to any given board state (higher scores to better board states). • learning task in this case to the problem of discovering an operational description of the ideal target function V. • learning algorithms acquires only some approximation to the target function, thus the process of learning the target function is often called function approximation.
- 24. Designing a programto learn to play checkers • Choosing a Representation for the Target Function: • We again have many options to represent TF: • using a large table with a distinct entry specifying the value for each distinct board state. • using a collection of rules that match against features of the board state • using a quadratic polynomial function of predefined board features • using an artificial neural network. • We wish to pick a very expressive representation to allow representing as close an approximation as possible to the ideal target function. • The more expressive the representation, the more training data the program will require.
- 25. Designing a programto learn to play checkers • Choosing a Representation for the Target Function: • for example, we can calculate the function as a linear combination of the following board features: • x1: the number of black pieces on the board • x2: the number of white pieces on the board • x3: the number of black kings on the board • x4: the number of white kings on the board • x5: the number of black pieces threatened by white (i.e., which can be captured on white's next turn) • x6: the number of white pieces threatened by black where wo through w6 are numerical coefficients, or weights, to be chosen by the learning algorithm.
- 26. Designing a programto learn to play checkers • Estimating training values • While it is easy to assign a value to board states that correspond to the end of the game, it is less obvious how to assign training values to the more numerous intermediate board states that occur before the game's end. • Simple solution: • Adjusting the weights • We seek the weights, or equivalently the , that minimize E for the observed training examples. • Choosing a Function Approximation Algorithm: Final design of the checkers learning program
- 27. Type of MachineLearning Problem: Supervised, Unsupervised and Reinforced
- 28. Types of MachineLearning algorithms
- 29. Supervised/Directed Learning • Insupervised learning the machine experiences the examples along with the labels or targets for each example. • The labels in the data help the algorithm to correlate the features.
- 30. Supervised/Directed Learning • Twoof the most common supervised machine learning tasks are: • Classification: machine learns to predict discrete values • predicting whether a stock's price will rise or fall • deciding if a news article belongs to the politics or leisure section • Regression: machine predicts the value of a continuous response variable • predicting the sales for a new product • the salary for a job based on its description
- 31. Supervised/Directed Learning • Classification: •A classification problem is when the output variable is a category/class and the goal is to classify the input into the known categories/classes. • It basically aims to predict which class the input corresponds to. • Some examples include systems where we seek a yes-or-no prediction, such as: • “Is this tumour cancerous?”, • “Does this product meet our quality standards?”
- 32. Supervised/Directed Learning • Regression: •A regression problem is when the output variable is a real and continuous value. Here, the goal is to predict the output value given an input x. • Some examples include systems where the value being predicted falls somewhere on a continuous spectrum. • predicting the stock price of a company • predicting the temperature tomorrow based on historical data.
- 33. Supervised/Directed Learning • Commonlyused algorithms for classification and regression
- 34. Unsupervised/Undirected Learning • Whenwe have unclassified and unlabeled data, the system attempts to uncover patterns from the data . • There is no label or target given for the examples. • One common task is to group similar examples together called clustering. • clustering and association learning belong to this category
- 35. Unsupervised/Undirected Learning • Clustering: •Here the goal is to find similarities in the dataset and group similar data points together. • Cluster is the collection of data objects which are similar to one another within the same group (class or category) and are different from the objects in the other clusters. • This method can also be used to detect anomalies that do not fit to any group. • In marketing, customers are segmented according to similarities to carry out targeted marketing. • Given a collection of text, we need to organize them, according to the content similarities to create a topic hierarchy. • Detecting distinct kinds of pattern in image data (Image processing). • It’s effective in biology research for identifying the underlying patterns.
- 36. Unsupervised/Undirected Learning • Associationlearning: • In association learning, any relation between observations is required, not merely association capable of predicting a specific class value. • Here the aim is to discover rules that describe large portions of our data, such as people that buy X also tend to buy Y. • A classic example of association rules would be market basket analysis, like, a person who buys biryani and burgers usually buys a soft drink too.
- 37. Of the followingexamples, which would you address using an unsupervised learning algorithm? (Check all that apply.) Given a database of customer data, automatically discover market segments and group customers into different market segments. Given email labeled as spam/not spam, learn a spam filter. Given a set of news articles found on the web, group them into set of articles about the same story. Given a dataset of patients diagnosed as either having diabetes or not, learn to classify new patients as having diabetes or not.
- 39. Clustering vs clasification •In the case of Classification, there are predefined labels assigned to each input instance according to their properties • whereas in clustering those labels are missing. • The process of classifying the input instances based on their corresponding class labels is known as classification • whereas grouping the instances based on their similarity without the help of class labels is known as clustering.
- 40. Reinforcement Learning • Reinforcementlearning refers to goal-oriented algorithms, which learn how to attain a complex objective (goal) or maximize along a particular dimension over many steps. • This method allows machines to automatically determine the ideal behavior within a specific context in order to maximize its performance. • Simple reward feedback is required for the agent to learn which action is best; this is known as the reinforcement signal. • For example, maximize the points won in a game over many moves.
- 41. Semi-Supervised Learning • Problemswhere you have a large amount of input data (X) and only some of the data is labeled (Y) are called semi-supervised learning problems. • Many real world machine learning problems fall into this area. • This is because it can be expensive or time-consuming to label data as it may require access to domain experts, whereas, unlabeled data is cheap and easy to collect and store. • You can also use supervised learning techniques to make best guess predictions for the unlabeled data, feed that data back into the supervised learning algorithm as training data and use the model to make predictions on new unseen data.