Uczenie maszynowe
Dipanjan Sarkar, Raghav Bali, Tamoghna Ghosh
Transfer learning is a machine learning (ML) technique where knowledge gained during training a set of problems can be used to solve other similar problems. The purpose of this book is two-fold; firstly, we focus on detailed coverage of deep learning (DL) and transfer learning, comparing and contrasting the two with easy-to-follow concepts and examples. The second area of focus is real-world examples and research problems using TensorFlow, Keras, and the Python ecosystem with hands-on examples. The book starts with the key essential concepts of ML and DL, followed by depiction and coverage of important DL architectures such as convolutional neural networks (CNNs), deep neural networks (DNNs), recurrent neural networks (RNNs), long short-term memory (LSTM), and capsule networks. Our focus then shifts to transfer learning concepts, such as model freezing, fine-tuning, pre-trained models including VGG, inception, ResNet, and how these systems perform better than DL models with practical examples. In the concluding chapters, we will focus on a multitude of real-world case studies and problems associated with areas such as computer vision, audio analysis and natural language processing (NLP).By the end of this book, you will be able to implement both DL and transfer learning principles in your own systems.
Giuseppe Bonaccorso
Unsupervised learning is about making use of raw, untagged data and applying learning algorithms to it to help a machine predict its outcome. With this book, you will explore the concept of unsupervised learning to cluster large sets of data and analyze them repeatedly until the desired outcome is found using Python.This book starts with the key differences between supervised, unsupervised, and semi-supervised learning. You will be introduced to the best-used libraries and frameworks from the Python ecosystem and address unsupervised learning in both the machine learning and deep learning domains. You will explore various algorithms, techniques that are used to implement unsupervised learning in real-world use cases. You will learn a variety of unsupervised learning approaches, including randomized optimization, clustering, feature selection and transformation, and information theory. You will get hands-on experience with how neural networks can be employed in unsupervised scenarios. You will also explore the steps involved in building and training a GAN in order to process images.By the end of this book, you will have learned the art of unsupervised learning for different real-world challenges.
IBM Cloud Pak for Data. An enterprise platform to operationalize data, analytics, and AI
Hemanth Manda, Sriram Srinivasan, Deepak Rangarao
Cloud Pak for Data is IBM's modern data and AI platform that includes strategic offerings from its data and AI portfolio delivered in a cloud-native fashion with the flexibility of deployment on any cloud. The platform offers a unique approach to addressing modern challenges with an integrated mix of proprietary, open-source, and third-party services.You'll begin by getting to grips with key concepts in modern data management and artificial intelligence (AI), reviewing real-life use cases, and developing an appreciation of the AI Ladder principle. Once you've gotten to grips with the basics, you will explore how Cloud Pak for Data helps in the elegant implementation of the AI Ladder practice to collect, organize, analyze, and infuse data and trustworthy AI across your business. As you advance, you'll discover the capabilities of the platform and extension services, including how they are packaged and priced. With the help of examples present throughout the book, you will gain a deep understanding of the platform, from its rich capabilities and technical architecture to its ecosystem and key go-to-market aspects.By the end of this IBM book, you'll be able to apply IBM Cloud Pak for Data's prescriptive practices and leverage its capabilities to build a trusted data foundation and accelerate AI adoption in your enterprise.
James D. Miller
IBM Watson provides fast, intelligent insight in ways that the human brain simply can't match. Through eight varied projects, this book will help you explore the computing and analytical capabilities of IBM Watson.The book begins by refreshing your knowledge of IBM Watson's basic data preparation capabilities, such as adding and exploring data to prepare it for being applied to models. The projects covered in this book can be developed for different industries, including banking, healthcare, media, and security. These projects will enable you to develop an AI mindset and guide you in developing smart data-driven projects, including automating supply chains, analyzing sentiment in social media datasets, and developing personalized recommendations.By the end of this book, you'll have learned how to develop solutions for process automation, and you'll be able to make better data-driven decisions to deliver an excellent customer experience.
Inteligentna sieć. Algorytmy przyszłości. Wydanie II
Douglas McIlwraith, Haralambos Marmanis, Dmitry Babenko
Określenie „inteligentna sieć” może przywodzić na myśl futurystyczną wizję maszyn przejmujących kontrolę nad światem i niszczących ludzkość, jednak w rzeczywistości jest związane z rozwojem technologii. Związane jest z powstawaniem oprogramowania, które potrafi się uczyć i reagować na zachowania użytkowników. Oznacza też projektowanie i implementację inteligencji maszynowej. Inteligentna sieć rozwija się tu i teraz — znajomość zagadnień uczenia maszynowego i budowy inteligentnych algorytmów staje się bardzo potrzebna inżynierom oprogramowania! Niniejsza książka jest przeznaczona dla osób, które chcą projektować inteligentne algorytmy, a przy tym mają podstawy z zakresu programowania, matematyki i statystyki. Przedstawiono tu schematy projektowe i praktyczne przykłady rozwiązań. Opisano algorytmy, które przetwarzają strumienie danych pochodzące z internetu, a także systemy rekomendacji i klasyfikowania danych za pomocą algorytmów statystycznych, sieci neuronowych i uczenia głębokiego. Mimo że przyswojenie tych zagadnień wymaga wysiłku, bardzo ułatwi implementację nowoczesnych, inteligentnych aplikacji! W tej książce między innymi: wprowadzenie do problemów algorytmów inteligentnych systemy rekomendacji i filtrowanie kolaboratywne wykorzystanie regresji logistycznej do wykrywania oszustw uczenie głębokie, uczenie na żywo i renesans sieci neuronowych podejmowanie decyzji perspektywy inteligentnej sieci Inteligentny algorytm wyławia perły w strumieniach danych! Dr Douglas McIlwraith jest ekspertem w dziedzinie uczenia maszynowego. Zajmuje się analizą danych w londyńskiej agencji reklamowej. Prowadził badania w dziedzinach systemów rozproszonych, robotyki i zabezpieczeń. Dr Haralambos Marmanis jest pionierem w obszarze technik uczenia maszynowego w rozwiązaniach przemysłowych. Od 25 lat rozwija profesjonalne oprogramowanie. Dmitry Babenko projektuje złożone systemy dla firm z takich branż, jak bankowość, ubezpieczenia, zarządzanie łańcuchem dostaw i analityka biznesowa.
Santanu Pattanayak, Manohar Swamynathan
This book will be a perfect companion if you want to build insightful projects from leading AI domains using Python.The book covers detailed implementation of projects from all the core disciplines of AI. We start by covering the basics of how to create smart systems using machine learning and deep learning techniques. You will assimilate various neural network architectures such as CNN, RNN, LSTM, to solve critical new world challenges. You will learn to train a model to detect diabetic retinopathy conditions in the human eye and create an intelligent system for performing a video-to-text translation. You will use the transfer learning technique in the healthcare domain and implement style transfer using GANs. Later you will learn to build AI-based recommendation systems, a mobile app for sentiment analysis and a powerful chatbot for carrying customer services. You will implement AI techniques in the cybersecurity domain to generate Captchas. Later you will train and build autonomous vehicles to self-drive using reinforcement learning. You will be using libraries from the Python ecosystem such as TensorFlow, Keras and more to bring the core aspects of machine learning, deep learning, and AI.By the end of this book, you will be skilled to build your own smart models for tackling any kind of AI problems without any hassle.
Indraneel (Neel) Mitra, Ryan Burke
The Internet of Things (IoT) has transformed how people think about and interact with the world. The ubiquitous deployment of sensors around us makes it possible to study the world at any level of accuracy and enable data-driven decision-making anywhere. Data analytics and machine learning (ML) powered by elastic cloud computing have accelerated our ability to understand and analyze the huge amount of data generated by IoT. Now, edge computing has brought information technologies closer to the data source to lower latency and reduce costs.This book will teach you how to combine the technologies of edge computing, data analytics, and ML to deliver next-generation cyber-physical outcomes. You’ll begin by discovering how to create software applications that run on edge devices with AWS IoT Greengrass. As you advance, you’ll learn how to process and stream IoT data from the edge to the cloud and use it to train ML models using Amazon SageMaker. The book also shows you how to train these models and run them at the edge for optimized performance, cost savings, and data compliance.By the end of this IoT book, you’ll be able to scope your own IoT workloads, bring the power of ML to the edge, and operate those workloads in a production setting.
Serg Masís, Aleksander Molak, Denis Rothman
Interpretable Machine Learning with Python, Second Edition, brings to light the key concepts of interpreting machine learning models by analyzing real-world data, providing you with a wide range of skills and tools to decipher the results of even the most complex models.Build your interpretability toolkit with several use cases, from flight delay prediction to waste classification to COMPAS risk assessment scores. This book is full of useful techniques, introducing them to the right use case. Learn traditional methods, such as feature importance and partial dependence plots to integrated gradients for NLP interpretations and gradient-based attribution methods, such as saliency maps.In addition to the step-by-step code, you’ll get hands-on with tuning models and training data for interpretability by reducing complexity, mitigating bias, placing guardrails, and enhancing reliability.By the end of the book, you’ll be confident in tackling interpretability challenges with black-box models using tabular, language, image, and time series data.