Deep learning in practice / Mehdi Ghayoumi.

Format:

Book

Author/Creator:

Ghayoumi, Mehdi, author.

Contributor:

Taylor & Francis eBooks.

Language:

English

Subjects (All):

Deep learning (Machine learning).

Physical Description:

1 online resource (xx, 198 pages)

polychrome

Place of Publication:

Boca Raton, FL : CRC Press, 2022.

System Details:

text file

Biography/History:

Dr. Mehdi Ghayoumi is a course facilitator at Cornell University and adjunct faculty of Computer Science at the University of San Diego. Prior to this, he was a research assistant professor at SUNY at Binghamton, where he was the Media Core Lab⁰́₉s dynamic leader. He was also a lecturer at Kent State University, where he received the Teaching Award for two consecutive years in 2016 and 2017. In addition, he has been teaching machine learning, data science, robotic and programming courses for several years. Dr. Ghayoumi research interests are in Machine Learning, Machine Vision, Robotics, and Human-Robot Interaction (HRI). His research focuses are on building real systems for realistic environment settings, and his current projects have applications in Human-Robot Interaction, manufacturing, biometric, and healthcare. He is a technical program committee member of several conferences, workshops, and editorial board member of several journals in machine learning, mathematics, and robotics, like ICML, ICPR, HRI, FG, WACV, IROS, CIBCB, and JAI. In addition, his research papers have been published at conferences and journals in the fields, including Human-Computer Interaction (HRI), Robotics Science and Systems (RSS), International Conference on Machine Learning and Applications (ICMLA), and others.

Contents:

PrefaceAcknowledgementsAbout the Author1. Introduction 1.1 What is Learning?1.2 What is Machine Learning?1.3 What is Deep Learning?1.4 About this Book!1.4.1 Introduction1.4.2 Python /NumPy1.4.3 TensorFlow and Keras fundamentals1.4.4 Artificial Neural Networks (ANNs) Fundamentals and Architectures1.4.5 Deep Neural Networks (DNNs) Fundamentals and Architectures1.4.6 Deep Neural Networks for Images and Audio Data Analysis1.4.7 Deep Neural Networks for Virtual Assistant Robots1.4.8 What is the best model?2. Python/NumPy Fundamentals2.1 Python2.1.1 Variables2.1.2 Keywords2.1.3 Operators and Operand2.1.4 Statements and Expressions2.1.5 Sequence2.1.6 For Loop2.1.7 While Loop2.1.8 String2.1.9 List2.1.10 Dictionary2.1.11 Tuple2.1.12 Sets2.1.13 Function2.1.14 File2.1.15 Object (class)2.2 NumPy2.2.1 Create Array2.2.2 ndarray2.2.3 Access Elements2.2.4 Array Slicing2.2.5 Data Type2.2.6 Array Data Check2.2.7 Shape and Reshape Array2.2.8 Array Iterating2.2.9 Joining Array2.2.10 Splitting Array2.2.11 Searching Arrays2.2.12 Sorting Arrays2.2.13 Filter Array2.2.14 Random Numbers2.2.15 Array Vectorization2.2.16 np.zeros and np.ones2.2.17 hstack and vstack2.2.18 Generate Random Numbers2.2.19 Mathematical Functions2.2.20 Dot Product and Matrix Multiplication2.2.21 Determinant3. TensorFlow Fundamentals3.1 How TensorFlow Works?3.2 Tensors3.3 TensorFlow3.4 Building a NN Using TensorFlow3.4.1 Import the Data3.4.2 Loading and Normalize the Data3.4.3 Build the Model3.4.4 Train and Evaluate the Model3.5 Building a CNN Using TensorFlow3.5.1 Dataset3.5.2 Input Layer3.5.3 Convolutional and Pooling Layers3.5.4 Dense Layer3.5.5 Train and Evaluate the Model3.5.6 Test the Model3.6 Setup and Install Keras3.6.1 Create a Virtual Environment3.6.2 Activate the Environment3.6.3 Python Libraries3.6.4 Available Modules3.6.5 Import Libraries and Modules3.6.6 Train and Predict the Model3.7 Implement an Example Using Keras3.7.1 MNIST Example4. Artificial Neural Networks Fundamentals and Architectures4.1 Terminology4.1.1 Inputs4.1.2 Weights4.1.3 Outputs4.1.4 Targets4.1.5 Activation Function4.1.6 Error4.1.7 Training, Testing, and Validation Sets4.1.8 Overfitting4.1.9 Underfitting4.1.10 Confusion Matrix4.1.11 Accuracy Metrics4.1.12 Balanced and Unbalanced Datasets4.1.13 One Hot Encoding4.2 Artificial Neural Networks (ANNs)4.2.1 Biological Neuron4.2.2 Artificial Neuron4.3 Activation Functions4.3.1 Sigmoid (sig)4.3.2 Tanh or Hyperbolic Tangent (tan)4.3.3 Rectified Linear Unit (ReLU)4.3.4 Leaky ReLU4.4 Loss Functions4.4.1 Cross-Entropy Loss4.4.2 MSE (L2) Loss4.5 Optimization Functions4.5.1 Learning Rate4.5.2 Convex4.5.3 Gradient Descent4.5.4 Stochastic Gradient Descent4.5.5 Adagrad4.5.6 Adam4.6 Linear and Nonlinear Functions4.6.1 Linear Function4.6.2 Nonlinear Functions4.7 ANNs architectures4.7.1 Feed Forward Neural Networks (FFNNs)4.7.1.1 FFN Example in TensorFlow4.7.2 Backpropagation4.7.3 Single-layer perceptron4.7.4 Multi-Layer Perceptron (MLP)4.7.4.1 MLP Example in TensorFlow5. Deep Neural Networks (DNNs)Fundamentals and Architectures5.1 Deep Neural Networks (DNNs)5.1.1 What is Deep Learning?5.1.2 Deep Learning Needs!5.1.3 How to deploy DL More Efficiently?5.1.4 Vanishing Gradient5.1.5 Channel5.1.6 Embedding5.1.7 Fine-Tuning5.1.8 Data Augmentation5.1.9 Generalization5.1.10 Regularization5.1.11 L1 and L25.1.12 Dropout5.1.13 End-to-End Learning5.2 Deep Learning Applications5.3 Deep Learning Algorithms and Architectures5.3.1 Convolutional Neural Networks (CNNs)5.3.2 Recurrent Neural Networks (RNNs)5.3.3 Long Short-Term Memory (LSTM)5.3.4 Generative Adversarial Network (GAN)5.3.5 Residual Neural Network Learning ResNets5.4 Convolutional Neural Networks (CNNs)5.4.1 CNN Layers5.4.1.1 Convolution Layers5.4.1.2 Pooling Layers5.4.1.3 Dropout5.4.1.4 Batch Normalization5.4.1.5 Fully Connected Llayer5.4.2 Design a CNN5.5 Recurrent Neural Networks (RNNs)5.5.1 Recurrent Neural Network Architecture5.5.2 Long Short-Term Memory (LSTM)5.5.3 Designing an RNN5.5.3.1 Import Libraries5.5.3.2 Load and Normalize the Dataset5.5.3.3 Build the Model5.5.3.4 Train the Model5.5.3.5 Evaluate the Model5.6 Generative Adversarial Networks (GANs)5.6.1 What is a GAN?5.6.2 A GAN for Fashion Dataset5.6.2.1. Loading Dataset5.6.2.2 Data Preprocessing5.6.2.3 Defining the Discriminator Model5.6.2.4 Defining the Generator Model5.6.2.5 Combining the Generator and Discriminator Model5.6.2.6 Create Train Function and Train the Model5.6.2.7 Predict (generate data)6. Deep Neural Networks(DNNs) for Images Analysis6.1 Deep Learning and Image Analysis6.2 Convolutional Neural Networks (CNNs) and Image Analysis6.2.1 Filter Parameters6.2.1.1 Number and Type of Filters6.2.1.2 Filters Size6.2.1.3 Stride and Padding Size6.2.2 Number of Parameters6.2.2.1 Input Layer6.2.2.2 Convolutional Layer6.2.2.3 Pooling Layer6.2.2.4 Fully Connected Layer (FC)6.2.3 Imagenet Challenge6.2.4 CNN Architecture6.2.4.1 LeNet-5 (1998)6.2.4.2 AlexNet (2012)6.2.4.3 GoogleNet / Inception-v1 (2014)6.2.4.4 VGGNet-16 (2014)6.2.4.5 Inception-v3 (2015)6.2.4.6 ResNet (2015)6.2.4.7 Inception-v4 (2016)6.3 General Strategy to Implement Model Using CNNs6.3.1. Import Libraries6.3.2. Load the Data and Create the Data Categories6.3.3. Make the Model6.3.4. Train the Model6.3.5. Test the Mode6.4 Object Recognition Using CNNs6.4.1. Import Libraries6.4.2. Load the Data and Generate a Dataset6.4.3. Make the Model6.4.4. Train the Model6.4.5. Test the Model6.5 Image Classification Using CNNs6.5.1. Import Libraries6.5.2. Load the Data6.5.3. Make the Model6.5.4. Train the Model6.5.5. Test the Model6.6 Image Segmentation6.6.1. Import Libraries6.6.2. Load the Data and Generate a Dataset6.6.3. Segmentation Map6.6.4. Make the Model6.6.5. Train the Model6.6.6. Test the Model6.7 Object Recognition Using CNNs6.7.1. Import Libraries6.7.2. Load the Data and Generate a Dataset6.7.3. Make the Model6.7.3.1 The Generator Function6.3.7.2 The Discriminator Function6.7.4. Train the Model6.7.5. Generate images7. Deep Neural Networks for Virtual Assistant Robot7.1 Virtual Assistant Robot7.2 Facial Detection and Recognition7.2.1 Architecture7.2.2 Face Detection7.2.2.1 Import Libraries7.2.2.2 Dataset7.2.2.3 Define CNN Model and Training7.2.2.4 Model Training7.2.2.5 Evaluate Performance7.2.3 Landmark Detection7.2.3.1 CNN Model7.2.3.2 Model Training7.2.3.3 Test the Trained Model7.2.4 Spoof Detection7.2.5 Encoding the Face7.2.6 Training7.2.7 Testing7.3 Emotion Recognition Using Speech7.3.1 Dataset Collection7.3.2 Data Preprocessing7.3.2.1 Labeling7.3.2.2 Feature Extraction7.3.2.3 Data Augmentation7.3.3 Model Training7.3.4 Model Evaluation7.3.5 Test the Trained Model7.4 Speech to Text7.4.1. Feature Extraction7.4.2. Deep Neural Networks Modeling7.4.3. Decoder7.4.4. Predictions Calculation7.5 Sentiment Analysis7.5.1. Load Dataset7.5.2. Create a DAN Network7.5.3. Train the Network7.5.4. Evaluate the Model8. Finding the Best Model8.1 Data Preprocessing8.2 What is a Good Model?8.3 What is the Noise?8.3.1 Labeling8.3.2 Features8.4 What is the Bias?8.4.1 Incorrect Classifier8.4.2 Incorrect Features8.5 What is the Variance?8.5.1. New Dataset8.6 Bias/Variance8.7 How Can We Find the Problems in a Model?8.7.1 High Variance8.7.2 High BiasReferencesIndex

Notes:

Electronic reproduction. London Available via World Wide Web.

ISBN:

9781003025818

1003025811

9781000483390

1000483398

9781000483352

1000483355

Publisher Number:

40030861004

Access Restriction:

Restricted for use by site license.