Deep Learning Patterns and Practices, Video Edition

Deep Learning Patterns and Practices, Video Edition

English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 89 Lessons (13h 53m) | 1.48 GB

Discover best practices, reproducible architectures, and design patterns to help guide deep learning models from the lab into production.

In Deep Learning Patterns and Practices you will find:

  • Internal functioning of modern convolutional neural networks
  • Procedural reuse design pattern for CNN architectures
  • Models for mobile and IoT devices
  • Assembling large-scale model deployments
  • Optimizing hyperparameter tuning
  • Migrating a model to a production environment

The big challenge of deep learning lies in taking cutting-edge technologies from R&D labs through to production. Deep Learning Patterns and Practices is here to help. This unique guide lays out the latest deep learning insights from author Andrew Ferlitsch’s work with Google Cloud AI. In it, you’ll find deep learning models presented in a unique new way: as extendable design patterns you can easily plug-and-play into your software projects. Each valuable technique is presented in a way that’s easy to understand and filled with accessible diagrams and code samples.

Discover best practices, design patterns, and reproducible architectures that will guide your deep learning projects from the lab into production. This awesome book collects and illuminates the most relevant insights from a decade of real world deep learning experience. You’ll build your skills and confidence with each interesting example.

Deep Learning Patterns and Practices is a deep dive into building successful deep learning applications. You’ll save hours of trial-and-error by applying proven patterns and practices to your own projects. Tested code samples, real-world examples, and a brilliant narrative style make even complex concepts simple and engaging. Along the way, you’ll get tips for deploying, testing, and maintaining your projects.

Table of Contents

1 Part 1. Deep learning fundamentals
2 Designing modern machine learning
3 The evolution in machine learning approaches
4 Next steps in computer learning – Part 1
5 Next steps in computer learning – Part 2
6 The benefits of design patterns
7 Deep neural networks
8 Sequential API method
9 Activation functions
10 DNN binary classifier
11 Simple image classifier
12 Convolutional and residual neural networks
13 Feature detection
14 The ConvNet design for a CNN
15 VGG networks
16 Architecture
17 Batch normalization
18 Training fundamentals
19 Dataset splitting
20 Data normalization
21 Validation and overfitting
22 Convergence
23 Hyperparameters
24 Learning rate
25 Invariance
26 Scale invariance
27 Raw (disk) datasets
28 Resizing
29 Part 2. Basic design pattern
30 Procedural design pattern
31 Stem component
32 ResNet
33 Pre-stem
34 Task component
35 Beyond computer vision – NLP
36 Wide convolutional neural networks
37 Inception v1 module
38 Inception v2 – Factoring convolutions
39 Normal convolution
40 ResNeXt – Wide residual neural networks
41 Beyond computer vision – Structured data
42 Alternative connectivity patterns
43 Dense block
44 Xception – Extreme Inception
45 Exit flow of Xception
46 SE-Net – Squeeze and excitation
47 Mobile convolutional neural networks
48 Stem
49 MobileNet v2
50 SqueezeNet
51 Classifier
52 ShuffleNet v1
53 Learner
54 Deployment
55 Autoencoders
56 Convolutional autoencoders
57 Super-resolution
58 Pretext tasks
59 Part 3. Working with pipelines
60 Hyperparameter tuning
61 Lottery hypothesis
62 Hyperparameter search fundamentals
63 Random search
64 Learning rate scheduler
65 Regularization
66 Transfer learning
67 New classifier
68 TF Hub prebuilt models
69 Distinct tasks
70 Data distributions
71 Out of distribution
72 Training as a CNN
73 Data pipeline
74 Compressed and raw-image formats
75 HDF5 format
76 TFRecord format
77 Data feeding
78 Data preprocessing
79 Preprocessing with TF Extended
80 Data augmentation
81 Training and deployment pipeline
82 Model feeding with tf.data.Dataset
83 Model feeding with TFX
84 Training schedulers
85 Model evaluations
86 TFX evaluation
87 Serving predictions
88 TFX pipeline components for deployment
89 Evolution in production pipeline design

Homepage