IBM Cognitive Class
Autoencoders and Regularization – Learn and Implement
In this course, you'll explore how Autoencoders compress, denoise, and derive valuable features from data. You'll also delve into regularization to curb overfitting and boost model generalizability. Autoencoders play roles in image enhancement, anomaly spotting, recommendation engines, and generative modelling. Meanwhile, regularization is essential in nearly every machine-learning endeavor. This training will equip you to address practical challenges across various applications. In today's data-driven world, professionals with expertise in data preprocessing and model optimization are in high demand. Autoencoders are a powerful tool for data compression and feature extraction. In an era where data is abundant but often noisy or high-dimensional, knowing how to effectively process and represent data is crucial. In addition, overfitting is a common challenge in machine learning. Regularization techniques are your shield against this problem. By learning how to apply regularization effectively, you'll be able to build models that generalize well to new, unseen data. IBM has a special offer for watsonx.ai a studio for new foundation models, generative AI and machine learning. To take advantage of this offer visit watsonx.ai homepage. Enroll and don't miss the chance to be at the forefront of AI innovation. Course Syllabus Topics that will be covered in the course Regularization Autoencoders Variational Autoencoders Recommended Skills Prior to Taking this Course A good understanding of Keras, Linear Regression and Classification and Neural Networks Principles in addition to Python programming language.
GratisLearn Recurrent Neural Networks Hands-On
In the real world, data often comes in sequences: text, speech, time-series data, and more. RNNs are the key to understanding and working with these sequential data types. By taking this course, you'll gain the essential knowledge and skills to handle and model sequences effectively. You will discover how RNNs revolutionize natural language processing, time series analysis, and more. This course is captivating for anyone interested in artificial intelligence, data science, or machine learning. If you've ever been fascinated by machines that can understand and generate human language, RNNs are at the core of these language models. This course will empower you to work on NLP tasks like sentiment analysis, chatbots, and machine translation. Time series data is everywhere, from financial markets to climate patterns. RNNs excel at modeling and forecasting time-dependent data. By taking this course, you'll be equipped to tackle real-world problems in fields like finance or weather forecasting and much more Enroll and don't miss the chance to be at the forefront of AI innovation. IBM has a special offer for watsonx.ai a studio for new foundation models, generative AI and machine learning. To take advantage of this offer visit watsonx.ai homepage. Course Syllabus Topics that will be cover in the course Types of Sequential Data Recurrent Neural Networks Long Short-Term Memory Word Embeddings Recommended Skills Prior to Taking this Course A good understanding of Keras, Linear Regression and Classification and Neural Networks Principles in addition to Python programming language.
GratisConvolutional Neural Networks with PyTorch
In this course you will gain practical skills to tackle real-world image analysis and computer vision challenges using PyTorch. Uncover the power of Convolutional Neural Networks (CNNs) and explore the fundamentals of convolution, max pooling, and convolutional networks. Learn to train your models with GPUs and leverage pre-trained networks for transfer learning. . Note, this course is a part of a PyTorch Learning Path, check Prerequisites Section. Course Syllabus Throughout the course, participants will dive deep into key topics and gain hands-on experience to master CNNs. The curriculum covers the following essential areas: Convolution: Understand the fundamental concept of convolution and its role in extracting meaningful features from images. Explore various filter operations and learn to apply convolutions effectively to uncover valuable patterns. Max Pooling: Delve into the concept of max pooling, a technique used to downsample feature maps and capture dominant features. Gain proficiency in incorporating max pooling layers within CNN architectures to enhance model performance. Convolutional Networks: Learn about the architecture and design principles of convolutional networks. Examine the different layers involved, such as convolutional layers, pooling layers, and fully connected layers. Grasp the significance of each layer and its impact on network performance. Training your Model with a GPU: Discover the advantages of leveraging GPUs for training CNNs. Learn to harness PyTorch's GPU capabilities to accelerate model training, optimize memory usage, and effectively manage GPU resources for enhanced performance. Pre-trained Networks: Uncover the power of pre-trained networks and transfer learning. Explore pre-trained CNN models like ResNet, VGG, and AlexNet, and gain insights into leveraging their knowledge for efficient solving of image analysis tasks. Prerequisites Note: this course is a part of PyTorch Learning Path and the following is required: Completion of PyTorch: Tensor, Dataset and Data Augmentation course Completion of Linear Regression with PyTorch course Completion of Classification with PyTorch course Completion of Build a Neural Network with PyTorch course or a good understanding of PyTorch Tensors and DataSets, Linear Regression and Classification, Neural Networks Principles.
GratisServerless Computing using Cloud Functions – Developer I
This course is designed to teach you serverless computing essentials which include how to develop serverless applications composed of loosely-coupled, microservice-like functions. You will get the opportunity to learn more about serverless programming and deployment models as well as its top use cases and design patterns. Additionally, you will be guided through several labs that demonstrate how to implement essential concepts including how to create, deploy, and invoke cloud-based functions, connect them to event sources for automation and expose them as web-accessible endpoints and APIs. LEARNING OBJECTIVES After you complete this course, you will be able to: Comprehend how serverless computing works and ways it can be used in cloud applications Distinguish use cases and patterns compatible with Serverless Create and manage serverless functions using the IBM Cloud Functions platform Use packages to organize your functions and create reusable building blocks Automate your functions using alarm events Expose functions as to the web accessible endpoints and as APIs that return different content types Navigate the web user interface to perform similar tasks that mirror CLI commands Course Syllabus Module 1 - Serverless essentials How serverless is simplifying the Ops landscape for developers Understand the basic serverless programming model and semantics of IBM Cloud Functions Differentiate a Function-as-a-Service (FaaS) from a Container-as-a-Service (CaaS) Top use cases for serverless How IBM Cloud Functions implements serverless Module 2 - Create and invoke actions (lab) Install lab prerequisites Create and invoke actions Use action parameters Retrieve action logs Asynchronous actions Practice action sequences Module 3 - Manage actions with packages (lab) Use packaged actions Create your own packages Module 4 - Connect actions to event sources (lab) Understand the concepts Create triggers Practice rules Connect trigger feeds Module 5 - Expose APIs from actions (lab) Understand the concepts Create web-enabled actions API management of web actions Module 6 - Use the Web User Interface (Web UI) create and invoke an action create triggers with implicit rules expose web actions create an API explore the monitoring dashboard General Information It is self-paced. It can be taken at any time. RECOMMENDED SKILLS PRIOR TO TAKING THIS COURSE Basic understanding of Cloud Computing (the concept). It is also helpful if you know Javascript, but not required
GratisClassification with PyTorch
Designed for students and enthusiasts, this course equips you with the knowledge and practical skills to build powerful and accurate classification models using PyTorch. It offers a hands-on learning experience, allowing you to apply your knowledge through coding exercises and lessons so by the end of the course, you will possess the skills to build, train, and evaluate classification models using PyTorch. "Classification with PyTorch" is a part of a PyTorch Learning Path, check Prerequisites. Throughout the course, students will learn how to construct linear models and implement logistic regression algorithms using PyTorch. They will gain proficiency in making predictions using logistic regression models and understanding the underlying probabilistic interpretation. Students will also delve into Bernoulli distribution maximum likelihood estimation and logistic regression cross-entropy, enabling them to effectively estimate model parameters and optimize them for classification tasks. Furthermore, the course covers the application of the softmax function for multiclass classification, providing students with the necessary knowledge to perform accurate and reliable multiclass classification using PyTorch. Syllabus In this course we will learn about: Linear Classifier and Logistic Regression Logistic Regression Prediction Bernoulli Distribution Maximum Likelihood Estimation Logistic Regression Cross Entropy Softmax Function Softmax PyTorch Prerequisites Note: this course is a part of PyTorch Learning Path and the following is required : Completion of PyTorch: Tensor, Dataset and Data Augmentation course Completion of Linear Regression with PyTorch course or Good understanding of PyTorch Tensors, DataSets and Linear Regression Skills Prior to Taking this Course Basic knowledge of Python programming language. Basic knowledge of PyTorch Framework Familiarity with fundamental concepts of machine learning and deep learning is beneficial but not mandatory.
GratisGenerative Adversarial Networks and Reinforcement Learning
Generative adversarial networks (GANs) and Reinforcement Learning (RL) are highly sought-after skills in the job market. Companies across various industries are looking for professionals who can harness the potential of these technologies to drive innovation and solve complex problems. Discover why GANs are hailed as a game-changers, offering the ability to generate life-like content and revolutionize fields like art, medicine, and more. Learn why RL is the cornerstone of AI breakthroughs, from autonomous driving to game-playing AI. By mastering GANs and RL, you'll become a valuable asset in today's AI-driven world. Learn about Generative Adversarial Networks, enabling the creation of realistic artificial data and images and explore Reinforcement Learning to teach AI agents how to learn and adapt in diverse environments. Whether you're an artist, designer, or content creator, you can use GANs to generate unique artwork, music, and more. Imagine creating entirely new art styles or generating stunning visuals for your projects – the possibilities are endless. Using Rl, you can build AI agents that learn from their environment, enabling them to excel in complex tasks like mastering games, optimizing resource allocation, and even providing personalized recommendations. IBM has a special offer for watsonx.ai a studio for new foundation models, generative AI and machine learning. To take advantage of this offer visit watsonx.ai homepage. Enroll and don't miss the chance to be at the forefront of AI innovation. Recommended Skills Prior to Taking this Course A good understanding of Keras, Linear Regression and Classification and Neural Networks Principles in addition to Python programming language.
GratisLinear Regression with PyTorch
Linear regression is one of the most used technique for prediction. This course will give you a comprehensive understanding of linear regression modelling using the PyTorch framework. Equipped with these skills, you will be prepared to tackle real-world regression problems and utilize PyTorch effectively for predictive analysis tasks. It focuses specifically on the implementation and practical application of linear regression algorithms for predictive analysis. Note, this course is a part of a PyTorch Learning Path, find more in the Prerequisites Section. Throughout the course, students will learn the fundamental concepts and techniques of linear regression. They will gain proficiency in constructing and training linear regression models using PyTorch, utilizing both single and multiple independent variables to predict continuous target variables. Using PyTorch, students will implement linear regression models and train them using gradient descent optimization algorithms. They will gain hands-on experience in adjusting model parameters, evaluating model performance, and making predictions on unseen data. Course Syllabus In this course we will learn about: Module 1: Linear Classifier and Logistic Regression Linear Regression Training Gradient Descent and Cost PyTorch Slope Linear Regression Training Module 2: Stochastic Gradient Descent and the Data Loader Mini-Batch Descent Optimization in PyTorch Training, Validation and Test Split Multiple Linear Regression Prediction Multiple Output Linear Regression Prerequisites Note: this course is a part of PyTorch Learning Path and the following is required Completion of PyTorch: Tensor, Dataset and Data Augmentation course or Good understanding of PyTorch Tensors and DataSets Skills Prior to Taking this Course Basic knowledge of Python programming language. Basic knowledge of PyTorch Framework
GratisClassification Methods: Problems and Solutions
This hands-on course will introduce you to the captivating world of classification, where data becomes organized, patterns emerge, and insights are uncovered! By understanding the power of classification, you will be able to predict outcomes based on existing data. You will learn the essential techniques for classifying data into distinct categories using Python libraries including scikit-learn and seaborn. Through practical labs and exercises, you will excel in solving real-world problems, making data-driven decisions, and unlocking valuable insights from data. Welcome to the world of classification, one of the main types of modelling families in supervised Machine Learning! Through a series of engaging labs, you will delve into the entire classification process, starting from preprocessing your data to training and evaluating models. Additionally, you will learn how to effectively visualize and interpret the results and to handle data sets with unbalanced classes. Classification serves as a critical foundation in data analysis, from categorizing data into their respective classes to training and fine-tuning generative LLMs that can generate new and meaningful content. In this course, different types of classification methods will be covered, showcasing which one is most suitable for a particular use case. By the end of this course, you should be able to: Differentiate between the uses and applications of classification and classification ensembles. Utilize logistic regression, KNN, and SVM models. Use decision tree and tree-ensemble models. Demonstrate proficiency in other ensemble methods for classification. Implement a variety of error metrics to compare the efficiency of various classification models to choose the one that suits your data the best. Employ oversampling and undersampling techniques to handle unbalanced classes in a dataset. IBM has a special offer for watsonx.ai, a studio for new foundation models, generative AI, and machine learning. To take advantage of this offer, visit the watsonx.ai. Enrol now and don't miss the chance to be at the forefront of AI innovation. Who Should Take this Course This course targets aspiring data scientists interested in acquiring hands-on experience with Supervised Machine Learning Classification techniques in a business setting. Recommended Skills Prior to Taking this Course To get the most out of this course, you should have familiarity with programming in a Python development environment, as well as a fundamental understanding of Data Cleaning, Exploratory Data Analysis, Calculus, Linear Algebra, Probability, and Statistics.
GratisDeveloping Distributed Applications Using ZooKeeper
ZooKeeper is a coordination service that provides sets of tools to help manage distributed applications. Building distributed applications comes with challenges that are intrinsic to distributed applications itself, which includes maintaining configuration information, groups, naming, and synchronization. ZooKeeper allows developers to handle these challenges to create robust distributed applications. ZooKeeper comes with a set of guarantees: sequential consistency, atomicity, single system image, reliability, and timeliness. This course will help you learn how to use ZooKeeper to keep your Big Data applications running smoothly despite the challenges of operating in a complex distributed environment. What will I get after passing this course? You will receive a completion certificate. This course is a component required to receive the IBM Explorer - Big Data Administration badge (upon completion of all badge criteria). COURSE SYLLABUS Lesson 1 - Introduction to ZooKeeper Describe distributed systems and the purpose of Zookeeper Describe the ZooKeeper consistency guarantees Describe the basics of Zookeeper components Describe the application of Zookeeper in Hadoop ecosystem and usage in other real-world scenarios. Lesson 2 - The ZooKeeper Data Model Understand ZooKeeper Components in detail Use ZooKeeper CLI to run commands and interact with ZooKeeper service Lesson 3 - Programming and Advanced Topics Manage ZooKeeper’s ACL and authentication to control permissions to the znodes Handle the various failure modes of ZooKeeper List the various ZooKeeper bindings and API Use the Java API to create a ZooKeeper application Use various ZooKeeper clients to work with ZooKeeper Understand how ZooKeeper works with ZooKeeper Atomic Broadcast (zab) Maintain your ZooKeeper environment with ZooKeeper administration GENERAL INFORMATION This course is self-paced. It can be taken at any time. It can be taken as many times as you wish. Requirements Hadoop Foundations I Recommended skills prior to taking this course Basic knowledge of operating systems (UNIX/Linux) Know how to work with the Eclipse IDE
Gratis
