Python: Advanced Guide to Artificial Intelligence: Expert machine learning systems and intelligent agents using Python

Description

Get up to speed with machine learning techniques and create smart solutions for different problemsKey FeaturesMaster supervised, unsupervised, and semi-supervised machine learning algorithms and their implementation Build deep learning models for object detection, image classification, and similarity learningDevelop, deploy, and scale end-to-end deep neural network models in a production environmentBook DescriptionGaining expertise in artificial intelligence requires an in-depth understanding of the most popular machine learning algorithms. With this book, you'll be able to explore the most widely used algorithms in supervised, unsupervised, and semi-supervised machine learning, and learn how to use them in the most effective way possible. From Bayesian models, to the MCMC algorithm, and even Hidden Markov models, this Learning Path will teach you how to extract features from your dataset and perform dimensionality reduction by making use of Python-based libraries.You'll use TensorFlow and Keras to build deep learning models with concepts such as transfer learning, generative adversarial networks, and deep reinforcement learning. Next, you'll discover TensorFlow1.x's advanced features, such as distributed TensorFlow with TF clusters, and also understand the deployment of production models with TensorFlow Serving. As you progress, the book will guide you on how to implement techniques related to object classification, object detection, and image segmentation.By the end of this Python book, you'll have gained in-depth knowledge of TensorFlow, along with the skills you need for solving artificial intelligence problems.This Learning Path includes content from the following Packt books:Mastering Machine Learning Algorithms by Giuseppe BonaccorsoMastering TensorFlow 1.x by Armando FandangoDeep Learning for Computer Vision by Rajalingappaa ShanmugamaniWhat you will learnGet up to speed with how a machine model can be trained, optimized, and evaluatedWork with autoencoders and generative adversarial networksExplore the most important reinforcement learning techniquesBuild end-to-end deep learning (CNN, RNN, and autoencoder) modelsDefine and train a model for image and video classificationDeploy your deep learning models and optimize them for high performanceWho this book is forThis Learning Path is for data scientists, machine learning engineers, and artificial intelligence engineers who want to delve into complex machine learning algorithms, calibrate models, and improve predictions of trained models. Basic knowledge of Python programming and machine learning concepts is required to get the most out of this book.Table of ContentsMachine Learning Model FundamentalsIntroduction to Semi-Supervised LearningGraph-Based Semi-Supervised LearningBayesian Networks and Hidden Markov ModelsEM Algorithm and ApplicationsHebbian Learning and Self-Organizing MapsClustering AlgorithmsAdvanced Neural ModelsClassical Machine Learning with TensorFlowNeural Networks and MLP with TensorFlow and KerasRNN with TensorFlow and KerasCNN with TensorFlow and KerasAutoencoder with TensorFlow and KerasTensorFlow Models in Production with TF ServingDeep Reinforcement LearningGenerative Adversarial NetworksDistributed Models with TensorFlow ClustersDebugging TensorFlow ModelsTensor Processing UnitsGetting StartedImage ClassificationImage RetrievalObject DetectionSemantic SegmentationSimilarity Learning