Hello Reader
Books in your Cart

Deep Learning For Dummies

Deep Learning For Dummies
-15 %
Deep Learning For Dummies
Product Views: 24
  • Sold by Wiley India
  • Seller Rating:    0 Reviews
  • Contact Seller
  • ₹594
    M.R.P.:
    ₹699
    Inclusive of all taxes
    Reward Points: 1498
    This book makes sense of those increasingly confusing algorithms, and it creates a simple and safe environment to experiment with deep learning. It develops a sense of precisely what deep learning can do at a high level and then it provides examples of the major deep learning application types. The book includes simple example code, but there is also approachable text with real world examples, and even some hands on activities. The reader learns the topic in more than one way and from more than one perspective. _x000D_ John Mueller is a freelance author and technical editor. He has writing in his blood, having produced 108 books and more than 600 articles to date. The topics range from networking to home security and from database management to heads-down programming. Some of his current..

    Book Details

    Pustak Details
    Sold By Wiley India
    Author John Paul Mueller, Luca Massaron
    ISBN-13 9788126529988
    Edition 1st Edition
    Format Paperback
    Language English
    Pages 380 Pages
    Publication Year 2019

    Reviews

    Ask for Review

    Write a book review

    Book Description

    This book makes sense of those increasingly confusing algorithms, and it creates a simple and safe environment to experiment with deep learning. It develops a sense of precisely what deep learning can do at a high level and then it provides examples of the major deep learning application types. The book includes simple example code, but there is also approachable text with real world examples, and even some hands on activities. The reader learns the topic in more than one way and from more than one perspective. _x000D_ John Mueller is a freelance author and technical editor. He has writing in his blood, having produced 108 books and more than 600 articles to date. The topics range from networking to home security and from database management to heads-down programming. Some of his current books include AI for Dummies, Python for Data Science for Dummies, Machine Learning for Dummies, and Algorithms for Dummies, all of which require some knowledge of AI. _x000D_ _x000D_ Luca Massaron is a data scientist specialized in organizing and interpreting big data and transforming it into smart data by means of the simplest and most effective data mining and machine learning techniques. Because of his job as a quantitative marketing consultant and marketing researcher, he has been involved in quantitative data since 2000 with different clients and in various industries. _x000D_ Introduction _x000D_ About This Book _x000D_ Foolish Assumptions _x000D_ Icons Used in This Book _x000D_ Beyond the Book _x000D_ Where to Go from Here _x000D_ _x000D_ Part 1: Discovering Deep Learning _x000D_ Chapter 1: Introducing Deep Learning _x000D_ ·Defining What Deep Learning Means _x000D_ ·Starting from Artificial Intelligence _x000D_ ·Considering the role of AI _x000D_ ·Focusing on machine learning _x000D_ ·Moving from machine learning to deep learning _x000D_ ·Using Deep Learning in the Real World _x000D_ ·Understanding the concept of learning _x000D_ ·Performing deep learning tasks _x000D_ ·Employing deep learning in applications _x000D_ ·Considering the Deep Learning Programming Environment _x000D_ ·Overcoming Deep Learning Hype _x000D_ ·Discovering the start-up ecosystem _x000D_ ·Knowing when not to use deep learning _x000D_ _x000D_ Chapter 2: Introducing the Machine Learning Principles _x000D_ ·Defining Machine Learning _x000D_ ·Understanding how machine learning works _x000D_ ·Understanding that it's pure math _x000D_ ·Learning by different strategies _x000D_ ·Training, validating, and testing data _x000D_ ·Looking for generalization _x000D_ ·Getting to know the limits of bias _x000D_ ·Keeping model complexity in mind _x000D_ ·Considering the Many Different Roads to Learning _x000D_ ·Understanding there is no free lunch _x000D_ ·Discovering the five main approaches _x000D_ ·Delving into some different approaches _x000D_ ·Awaiting the next breakthrough _x000D_ ·Pondering the True Uses of Machine Learning _x000D_ ·Understanding machine learning benefits _x000D_ ·Discovering machine learning limits _x000D_ _x000D_ Chapter 3: Getting and Using Python _x000D_ ·Working with Python in this Book _x000D_ ·Obtaining Your Copy of Anaconda _x000D_ ·Getting Continuum Analytics Anaconda _x000D_ ·Installing Anaconda on Linux _x000D_ ·Installing Anaconda on MacOS _x000D_ ·Installing Anaconda on Windows _x000D_ ·Downloading the Datasets and Example Code _x000D_ ·Using Jupyter Notebook _x000D_ ·Defining the code repository _x000D_ ·Getting and using datasets _x000D_ ·Creating the Application _x000D_ ·Understanding cells _x000D_ ·Adding documentation cells _x000D_ ·Using other cell types _x000D_ ·Understanding the Use of Indentation _x000D_ ·Adding Comments _x000D_ ·Understanding comments _x000D_ ·Using comments to leave yourself reminders _x000D_ ·Using comments to keep code from executing _x000D_ ·Getting Help with the Python Language _x000D_ ·Working in the Cloud _x000D_ ·Using the Kaggle datasets and kernels _x000D_ ·Using the Google Colaboratory _x000D_ _x000D_ Chapter 4: Leveraging a Deep Learning Framework _x000D_ ·Presenting Frameworks _x000D_ ·Defining the differences _x000D_ ·Explaining the popularity of frameworks _x000D_ ·Defining the deep learning framework _x000D_ ·Choosing a particular framework _x000D_ ·Working with Low-End Frameworks _x000D_ ·Caffe2 _x000D_ ·Chainer _x000D_ ·PyTorch _x000D_ ·MXNet _x000D_ ·Microsoft Cognitive Toolkit/CNTK _x000D_ ·Understanding TensorFlow _x000D_ ·Grasping why TensorFlow is so good _x000D_ ·Making TensorFlow easier by using TFLearn _x000D_ ·Using Keras as the best simplifier _x000D_ ·Getting your copy of TensorFlow and Keras _x000D_ ·Fixing the C++ build tools error in Windows _x000D_ ·Accessing your new environment in Notebook _x000D_ _x000D_ Part 2: Considering Deep Learning Basics _x000D_ Chapter 5: Reviewing Matrix Math and Optimization _x000D_ ·Revealing the Math You Really Need _x000D_ ·Working with data _x000D_ ·Creating and operating with a matrix _x000D_ ·Understanding Scalar, Vector, and Matrix Operations _x000D_ ·Creating a matrix _x000D_ ·Performing matrix multiplication _x000D_ ·Executing advanced matrix operations _x000D_ ·Extending analysis to tensors _x000D_ ·Using vectorization effectively _x000D_ ·Interpreting Learning as Optimization _x000D_ ·Exploring cost functions _x000D_ ·Descending the error curve _x000D_ ·Learning the right direction _x000D_ ·Updating _x000D_ _x000D_ Chapter 6: Laying Linear Regression Foundations _x000D_ ·Combining Variables _x000D_ ·Working through simple linear regression _x000D_ ·Advancing to multiple linear regression _x000D_ ·Including gradient descent _x000D_ ·Seeing linear regression in action _x000D_ ·Mixing Variable Types _x000D_ ·Modeling the responses _x000D_ ·Modeling the features _x000D_ ·Dealing with complex relations _x000D_ ·Switching to Probabilities _x000D_ ·Specifying a binary response _x000D_ ·Transforming numeric estimates into probabilities _x000D_ ·Guessing the Right Features _x000D_ ·Defining the outcome of incompatible features _x000D_ ·Solving overfitting using selection and regularization _x000D_ ·Learning One Example at a Time _x000D_ ·Using gradient descent _x000D_ ·Understanding how SGD is different _x000D_ _x000D_ Chapter 7: Introducing Neural Networks _x000D_ ·Discovering the Incredible Perceptron _x000D_ ·Understanding perceptron functionality _x000D_ ·Touching the nonseparability limit _x000D_ ·Hitting Complexity with Neural Networks _x000D_ ·Considering the neuron _x000D_ ·Pushing data with feed-forward _x000D_ ·Going even deeper into the rabbit hole _x000D_ ·Using backpropagation to adjust learning _x000D_ ·Struggling with Overfitting _x000D_ ·Understanding the problem _x000D_ ·Opening the black box _x000D_ _x000D_ Chapter 8: Building a Basic Neural Network _x000D_ ·Understanding Neural Networks _x000D_ ·Defining the basic architecture _x000D_ ·Documenting the essential modules _x000D_ ·Solving a simple problem _x000D_ ·Looking Under the Hood of Neural Networks _x000D_ ·Choosing the right activation function _x000D_ ·Relying on a smart optimizer _x000D_ ·Setting a working learning rate _x000D_ _x000D_ Chapter 9: Moving to Deep Learning _x000D_ ·Seeing Data Everywhere _x000D_ ·Considering the effects of structure _x000D_ ·Understanding Moore's implications _x000D_ ·Considering what Moore's Law changes _x000D_ ·Discovering the Benefits of Additional Data _x000D_ ·Defining the ramifications of data _x000D_ ·Considering data timeliness and quality _x000D_ ·Improving Processing Speed _x000D_ ·Leveraging powerful hardware _x000D_ ·Making other investments _x000D_ ·Explaining Deep Learning Differences from Other Forms of AI _x000D_ ·Adding more layers _x000D_ ·Changing the activations _x000D_ ·Adding regularization by dropout _x000D_ ·Finding Even Smarter Solutions _x000D_ ·Using online learning _x000D_ ·Transferring learning _x000D_ ·Learning end to end _x000D_ _x000D_ Chapter 10: Explaining Convolutional Neural Networks _x000D_ ·Beginning the CNN Tour with Character Recognition _x000D_ ·Understanding image basics _x000D_ ·Explaining How Convolutions Work _x000D_ ·Understanding convolutions _x000D_ ·Simplifying the use of pooling _x000D_ ·Describing the LeNet architecture _x000D_ ·Detecting Edges and Shapes from Images _x000D_ ·Visualizing convolutions _x000D_ ·Unveiling successful architectures _x000D_ ·Discussing transfer learning _x000D_ _x000D_ Chapter 11: Introducing Recurrent Neural Networks _x000D_ ·Introducing Recurrent Networks _x000D_ ·Modeling sequences using memory _x000D_ ·Recognizing and translating speech _x000D_ ·Placing the correct caption on pictures _x000D_ ·Explaining Long Short-Term Memory _x000D_ ·Defining memory differences _x000D_ ·Walking through the LSTM architecture _x000D_ ·Discovering interesting variants _x000D_ ·Getting the necessary attention _x000D_ _x000D_ Part 3: Interacting with Deep Learning _x000D_ Chapter 12: Performing Image Classification _x000D_ ·Using Image Classification Challenges _x000D_ ·Delving into ImageNet and MS COCO _x000D_ ·Learning the magic of data augmentation _x000D_ ·Distinguishing Traffic Signs _x000D_ ·Preparing image data _x000D_ ·Running a classification task _x000D_ _x000D_ Chapter 13: Learning Advanced CNNs _x000D_ ·Distinguishing Classification Tasks _x000D_ ·Performing localization _x000D_ ·Classifying multiple objects _x000D_ ·Annotating multiple objects in images _x000D_ ·Segmenting images _x000D_ ·Perceiving Objects in Their Surroundings _x000D_ ·Discovering how RetinaNet works _x000D_ ·Using the Keras-RetinaNet code _x000D_ ·Overcoming Adversarial Attacks on Deep Learning Applications _x000D_ ·Tricking pixels _x000D_ ·Hacking with stickers and other artifacts _x000D_ _x000D_ Chapter 14: Working on Language Processing _x000D_ ·Processing Language _x000D_ ·Defining understanding as tokenization _x000D_ ·Putting all the documents into a bag _x000D_ ·Memorizing Sequences that Matter _x000D_ ·Understanding semantics by word embeddings _x000D_ ·Using AI for Sentiment Analysis _x000D_ _x000D_ Chapter 15: Generating Music and Visual Art _x000D_ ·Learning to Imitate Art and Life _x000D_ ·Transferring an artistic style _x000D_ ·Reducing the problem to statistics _x000D_ ·Understanding that deep learning doesn't create _x000D_ ·Mimicking an Artist _x000D_ ·Defining a new piece based on a single artist _x000D_ ·Combining styles to create new art _x000D_ ·Visualizing how neural networks dream _x000D_ ·Using a network to compose music _x000D_ _x000D_ Chapter 16: Building Generative Adversarial Networks _x000D_ ·Making Networks Compete _x000D_ ·Finding the key in the competition _x000D_ ·Achieving more realistic results _x000D_ ·Considering a Growing Field _x000D_ ·Inventing realistic pictures of celebrities _x000D_ ·Enhancing details and image translation _x000D_ _x000D_ Chapter 17: Playing with Deep Reinforcement Learning _x000D_ ·Playing a Game with Neural Networks _x000D_ ·Introducing reinforcement learning _x000D_ ·Simulating game environments _x000D_ ·Presenting Q-learning _x000D_ ·Explaining Alpha-Go _x000D_ ·Determining if you're going to win _x000D_ ·Applying self-learning at scale _x000D_ _x000D_ Part 4: The Part of Tens _x000D_ Chapter 18: Ten Applications that Require Deep Learning _x000D_ ·Restoring Color to Black-and-White Videos and Pictures _x000D_ ·Approximating Person Poses in Real Time _x000D_ ·Performing Real-Time Behavior Analysis _x000D_ ·Translating Languages _x000D_ ·Estimating Solar Savings Potential _x000D_ ·Beating People at Computer Games _x000D_ ·Generating Voices _x000D_ ·Predicting Demographics _x000D_ ·Creating Art from Real-World Pictures _x000D_ ·Forecasting Natural Catastrophes _x000D_ _x000D_ Chapter 19: Ten Must-Have Deep Learning Tools _x000D_ ·Compiling Math Expressions Using Theano _x000D_ ·Augmenting TensorFlow Using Keras _x000D_ ·Dynamically Computing Graphs with Chainer _x000D_ ·Creating a MATLAB-Like Environment with Torch _x000D_ ·Performing Tasks Dynamically with PyTorch _x000D_ ·Accelerating Deep Learning Research Using CUDA _x000D_ ·Supporting Business Needs with Deeplearning4j _x000D_ ·Mining Data Using Neural Designer _x000D_ ·Training Algorithms Using Microsoft Cognitive Toolkit (CNTK) _x000D_ ·Exploiting Full GPU Capability Using MXNet _x000D_ _x000D_ Chapter 20: Ten Types of Occupations that Use Deep Learning _x000D_ ·Managing People _x000D_ ·Improving Medicine _x000D_ ·Developing New Devices _x000D_ ·Providing Customer Support _x000D_ ·Seeing Data in New Ways _x000D_ ·Performing Analysis Faster _x000D_ ·Creating a Better Work Environment _x000D_ ·Researching Obscure or Detailed Information _x000D_ ·Designing Buildings _x000D_ ·Enhancing Safety _x000D_ _x000D_ Index

    Seller Featured Products