Chapter 5 - Machine which of Learning.pdf
- 1. Wolaita Sodo University School of Informatics Department of Computer Science Course title: Introduction to Artificial Intelligence Compiled by: Eyob S. (MSc)
- 3. Introduction • Learning is the only way that the agent can acquire what it needs to know. • Learning thus provides autonomy in the sense. • It also provides a good way to build high-performance systems by giving a learning system experience in the application domain. • The idea behind learning is that percepts should be used not only for acting, but also for improving the agent's ability to act in the future. • Learning takes place as a result of the interaction between the agent and the world, and from observation by the agent of its own decision- making processes.
- 4. Cont… • The most important distinction is between the learning element, which is responsible for making improvements, and the performance element, which is responsible for selecting external actions. • The learning element takes some knowledge about the learning element and some feedback on how the agent is doing, and determines how the performance element should be modified to do better in the future.
- 6. Cont… • The design of the learning element depends very much on the design of the performance element. • The critic is designed to tell the learning element how well the agent is doing. The critic employs a fixed standard of performance. • The last component of the learning agent is the problem generator and it is responsible for suggesting actions that will lead to new and informative experiences.
- 7. Cont… • Machine learning researchers have come up with a large variety of learning elements. • To understand them, it will help to see how their design is affected by the context in which they will operate. The design of the learning element is affected by four major issues: 1. Which components of the performance element are to be improved? 2. What representation is used for those components? 3. What feedback is available? 4. What prior information is available?
- 8. Components of the performance element 1. A direct mapping from conditions on the current state to actions. 2. A means to infer relevant properties of the world from the percept sequence. 3. Information about the way the world evolves. 4. Information about the results of possible actions the agent can take. 5. Utility information indicating the desirability of world states. 6. Action-value information indicating the desirability of particular actions in particular states. 7. Goals that describe classes of states whose achievement maximizes the agent's utility.
- 9. What is Machine Learning • Machine learning is an exciting field and a subset of artificial intelligence. • This field of study uses data and algorithms to mimic human learning, allowing machines to improve over time. Definition: • Machine learning is considered as a subfield of artificial intelligence that is concerned with competence to the computer systems or machines in order to improve the performance automatically without being explicitly programmed. • It works in three basic ways, starting with using a combination of data and algorithms to predict patterns and classify data sets, an error function that helps evaluate the accuracy, and then an optimization process to fit the data points into the model best. How does Machine Learning work?
- 10. Features of Machine Learning • Machine learning uses data to detect various patterns in a given dataset. • It can learn from past data and improve automatically (It is a data-driven technology). • Scalability: Machine learning techniques are well suited for processing big data because they are made to handle massive amounts of data. • Adaptiveness: As new data becomes available, machine learning algorithms are built to learn and adapt continuously. As a result, they can enhance their performance over time, becoming more precise and efficient as more data is made available to them.
- 11. Types of Machine Learning • Learning in AI classified into: Machine Learning and Deep Learning • Machine Learning also classified into:
- 12. 1. Supervised Learning • The system creates a model using labeled data to understand the datasets and learn about each data. • Once the training and processing are done then we test the model by providing a sample data to check whether it is predicting the exact output or not. E.g. Spam filtering (classify a mail as either “spam” or “not spam”). Supervised learning can be grouped further in two categories of algorithms: • Classification • Regression
- 13. Classification and Regression • Regression and Classification algorithms are Supervised Learning algorithms. • Classification is the process of recognizing, understanding, and grouping ideas and objects into preset categories or “sub- populations.” • But the difference between both is how they are used for different machine learning problems. • The main difference between Regression and Classification algorithms that Regression algorithms are used to predict the continuous values such as price, salary, etc. and classification algorithms are used to predict/Classify the discrete values such as Male or Female, True or False, Spam or Not Spam, etc.
- 14. Classification and Regression Algorithms Classification algorithms • Logistic Regression • Naive Byes • K-Nearest Neighbors • Decision Tree • Random Forest Algorithm • Support Vector Machine Regression algorithms • Linear Regression • Logistic regression • Lasso Regression • Polynomial regression
- 15. 2. Unsupervised Learning • Unsupervised learning is a learning method in which a machine learns without any supervision. • The training is provided to the machine with the set of data that has not been labeled, classified, or categorized, and the algorithm needs to act on that data without any supervision. • The goal of unsupervised learning is to restructure the input data into new features or a group of objects with similar patterns. • In unsupervised learning, we don't explicitly divide the data into training and testing sets. • It can be further classifieds into two categories of algorithms: • Clustering • Association
- 16. Unsupervised Learning Algorithms Below is the list of some popular unsupervised learning algorithms: • K-means clustering • Hierarchal clustering • Anomaly detection • Principle Component Analysis • Independent Component Analysis • Apriori algorithm • Singular value decomposition
- 17. 3. Reinforcement Learning • Reinforcement learning is a feedback- based learning method (trial and error), in which a learning agent gets a reward for each right action and gets a penalty for each wrong action. • The agent learns automatically with these feedbacks and improves its performance. • In reinforcement learning, the agent interacts with the environment and explores it. • The goal of an agent is to get the most reward points, and hence, it improves its performance. • RL solves a specific type of problem where decision making is sequential, and the goal is long-term, such as game-playing, robotics, self driving cars etc.
- 18. Reinforcement Learning Algorithms • Reinforcement learning algorithms are mainly used in AI applications and gaming applications. The main used algorithms are: • Q-Learning: • Q-learning is a key RL algorithm, which is used for the temporal difference Learning. The temporal difference learning methods are the way of comparing temporally successive predictions. • The main objective of Q-learning is to learn the policy which can inform the agent that what actions should be taken for maximizing the reward under what circumstances.
- 19. Machine learning Life cycle • Machine learning has given the computer systems the abilities to automatically learn without being explicitly programmed. • Machine learning life cycle is a cyclic process to build an efficient machine learning project. • The main purpose of the life cycle is to find a solution to the problem or project.
- 20. 1. Gathering Data • Data Gathering is the first step of the machine learning life cycle. • The goal of this step is to identify and obtain all data-related problems from internet, database, questionnaires, multimedia. • By performing the above task, we get a coherent set of data, also called as a dataset. This step includes the below tasks: • Identify various data sources • Collect data • Integrate the data obtained from different sources gathering data
- 21. 2. Data preparation • After collecting the data, we need to prepare it for further steps. • Data preparation is a step where we put our data into a suitable place and prepare it to use in our machine learning training. • This step can be further divided into two processes: Data exploration: • It is used to understand the nature of data that we have to work with. We need to understand the characteristics, format, and quality of data. Data pre-processing: • Now the next step is preprocessing of data for its analysis.
- 22. 3. Data Wrangling • Data wrangling is the process of cleaning and converting raw data into a useable format. • It is the process of cleaning the data, selecting the variable to use, and transforming the data in a proper format to make it more suitable for analysis in the next step. • In real-world applications, collected data may have various issues, including: • Missing Values • Duplicate data • Invalid data • Noise data (corrupted or distorted) • So, we use various filtering techniques to clean the data.
- 23. 4. Data Analysis • Now the cleaned and prepared data is passed on to the analysis step. This step involves: • Selection of analytical techniques • Building models • Review the result • The aim of this step is to build a machine learning model to analyze the data using various analytical techniques and review the outcome. • we select the machine learning techniques such as Classification, Regression, Cluster analysis, Association, etc. then build the model using prepared data, and evaluate the model.
- 24. 5. Train Model • Now the next step is to train the model, in this step we train our model to improve its performance for better outcome of the problem. • We use datasets to train the model using various machine learning algorithms. • Training a model is required so that it can understand the various patterns, rules, and, features.
- 25. 6. Test Model • Once our machine learning model has been trained on a given dataset, then we test the model. • In this step, we check for the accuracy of our model by providing a test dataset to it. • Testing the model determines the percentage accuracy of the model as per the requirement of project or problem.
- 26. 7. Deployment • The last step of machine learning life cycle is deployment, where we deploy the model in the real-world system. • If the above-prepared model is producing an accurate result as per our requirement with acceptable speed, then we deploy the model in the real system. • But before deploying the project, we will check whether it is improving its performance using available data or not. • The deployment phase is similar to making the final report for a project. adeemsa
- 27. Installing Anaconda and Python • In order to use Python for machine learning, we need to install it in our computer system with compatible IDEs (Integrated Development Environment). • Anaconda distribution provides installation of Python with various IDE's such as Jupyter Notebook, Spyder, Anaconda prompt, etc. How to download Anaconda?
- 30. Heart Disease classification using Python in Jupyter Notebook
- 32. TrainTest Split
- 33. Sklearn library for ML
- 34. Challenges and Limitations in Machine Learning • Machine learning projects encounter challenges such as data quality issues, insufficient data, and the need for robust model evaluation. Addressing these challenges is essential for the success of ML applications. • Current ML approaches have limitations including interpretability issues, susceptibility to bias, and challenges in handling complex, unstructured data. Understanding these limitations is crucial for responsible and effective deployment. machine learning write the zero law of robotics?
- 35. Deep Learning • Deep learning is based on the branch of machine learning, which is a subset of artificial intelligence. • Since neural networks imitate the human brain and so deep learning will do. In deep learning, nothing is programmed explicitly. • Deep learning models can achieve state-of-the-art accuracy, sometimes exceeding human-level performance. Models are trained by using a large set of labeled data and neural network architectures that contain many layers.
- 36. Deep Learning Algorithms Types of Algorithms used in Deep Learning: • Convolutional Neural Networks (CNNs) • Long Short Term Memory Networks (LSTMs) • Recurrent Neural Networks (RNNs) • Generative Adversarial Networks (GANs) • Radial Basis Function Networks (RBFNs) • Multilayer Perceptrons (MLPs) • Self Organizing Maps (SOMs) • Deep Belief Networks (DBNs)
- 37. Neural networks and Back-propagation What is Artificial Neural Network? • The term "Artificial Neural Network" is derived from Biological neural networks that develop the structure of a human brain. • Similar to the human brain that has neurons interconnected to one another, artificial neural networks also have neurons that are interconnected to one another in various layers of the networks. These neurons are known as nodes. • An artificial neural network has three or more layers that are interconnected. The first layer consists of input neurons. Those neurons send data on to the deeper layers, which in turn will send the final output data to the last output layer.
- 38. Cont… Input Layer: • As the name suggests, it accepts inputs in several different formats provided by the programmer. Hidden Layer: • The hidden layer presents in-between input and output layers. It performs all the calculations to find hidden features and patterns. Output Layer: • The input goes through a series of transformations using the hidden layer, which finally results in output that is conveyed using this layer.
- 39. Cont… Feed-Forward ANN: • A feed-forward network is a basic neural network comprising of an input layer, an output layer, and at least one layer of a neuron. • Through assessment of its output by reviewing its input, the intensity of the network can be noticed based on group behavior of the associated neurons, and the output is decided. Backpropagation • Backpropagation is one of the important concepts of a neural network. Our task is to classify our data best. • For this, we have to update the weights of parameter and bias, but how can we do that in a deep neural network? In the linear regression model, we use gradient descent to optimize the parameter. Similarly here we also use gradient descent algorithm using Backpropagation. artificial neural networks
- 40. Convolutional Neural Network • CNN is also known as ConvNets, consist of multiple layers and are mainly used for image processing and object detection. • Convolutional Neural Network are a special kind of neural network mainly used for image classification, clustering of images and object recognition. • DNNs enable unsupervised construction of hierarchical image representations. • To achieve the best accuracy, deep convolutional neural networks are preferred more than any other neural network. • CNNs process the data by passing it through multiple layers and extracting features to exhibit convolutional operations. Convolutional Neural Networks (CNNs) deep neural network: used to aims to mimic the information processing of the brain
- 41. Cont… • The Convolutional Layer consists of Rectified Linear Unit (ReLU) that outlasts to rectify the feature map. • The Pooling layer is used to rectify these feature maps into the next feed. Pooling is generally a sampling algorithm that is down-sampled and it reduces the dimensions of the feature map. • Fully Connected Layer which forms the flattened matrix or 2-D array fetched from the Pooling Layer as input and identifies the image by classifying it.
- 42. Long Short Term Memory Networks (LSTM) • RNN adds the immediate past to the present. • LSTMs can be defined as Recurrent Neural Networks (RNN) that are programmed to learn and adapt for dependencies for the long term. • It can memorize and recall past data for a greater period and by default, it is its sole behavior. • LSTMs are designed to retain over time and henceforth they are majorly used in time series predictions because they can restrain memory or previous inputs. • This analogy comes from their chain-like structure consisting of four interacting layers that communicate with each other differently. • Besides applications of time series prediction, they can be used to construct speech recognizers, development in pharmaceuticals, and others. used for sequential data processing
- 43. Cont…