Applied Deep Learning with Keras

Applied Deep Learning with Keras

English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 9h 02m | 12.9 GB

Take your neural networks to a whole new level with the simplicity and modularity of Keras, the most commonly used high-level neural networks API

Though designing neural networks is a sought-after skill, it is not easy to master. With Keras, you can apply complex machine learning algorithms with minimum code.

Applied Deep Learning with Keras starts by taking you through the basics of machine learning and Python all the way to gaining an in-depth understanding of applying Keras to develop efficient deep learning solutions. To help you grasp the difference between machine and deep learning, the course guides you on how to build a logistic regression model, first with scikit-learn and then with Keras. You will delve into Keras and its many models by creating prediction models for various real-world scenarios, such as disease prediction and customer churning. You’ll gain knowledge on how to evaluate, optimize, and improve your models to achieve maximum information. Next, you’ll learn to evaluate your model by cross-validating it using Keras Wrapper and scikit-learn. Following this, you’ll proceed to understand how to apply L1, L2, and dropout regularization techniques to improve the accuracy of your model. To help maintain accuracy, you’ll get to grips with applying techniques including null accuracy, precision, and AUC-ROC score techniques for fine tuning your model.

By the end of this course, you will have the skills you need to use Keras when building high-level deep neural networks.

Learn

  • Understand the difference between single-layer and multi-layer neural network models
  • Use Keras to build simple logistic regression models, deep neural networks, recurrent neural networks, and convolutional neural networks
  • Apply L1, L2, and dropout regularization to improve the accuracy of your model
  • Implement cross-validate using Keras wrappers with scikit-learn
  • Understand the limitations of model accuracy
Table of Contents

Introduction to Machine Learning with Keras
1 Course Overview
2 Installation and Setup
3 Lesson Overview
4 Data Representation
5 Loading a Dataset from the UCI Machine Learning Repository
6 Data Pre-Processing
7 Cleaning the Data
8 Appropriate Representation of the Data
9 Lifecycle of Model Creation
10 Machine Learning Libraries and scikit-learn
11 Keras
12 Model Training
13 Creating a Simple Model
14 Model Tuning
15 Regularization
16 Lesson Summary

Machine Learning versus Deep Learning
17 Lesson Overview
18 Introduction to ANNs
19 Linear Transformations
20 Matrix Transposition
21 Introduction to Keras
22 Lesson Summary

Deep Learning with Keras
23 Lesson Overview
24 Building Your First Neural Network
25 Gradient Descent for Learning the Parameters
26 Model Evaluation
27 Lesson Summary

Evaluate Your Model with Cross-Validation using Keras Wrappers
28 Lesson Overview
29 Cross-Validation
30 Cross-Validation for Deep Learning Models
31 Evaluate Deep Neural Networks with Cross-Validation
32 Model Selection with Cross-validation
33 Write User-Defined Functions to Implement Deep Learning Models with Cross-Validation
34 Lesson Summary

Improving Model Accuracy
35 Lesson Overview
36 Regularization
37 L1 and L2 Regularization
38 Dropout Regularization
39 Other Regularization Methods
40 Data Augmentation
41 Hyperparameter Tuning with scikit-learn
42 Lesson Summary

Model Evaluation
43 Lesson Overview
44 Accuracy
45 Imbalanced Datasets
46 Confusion Matrix
47 Computing Accuracy and Null Accuracy with Healthcare Data
48 Calculate the ROC and AUC Curves
49 Lesson Summary

Computer Vision with Convolutional Neural Networks
50 Lesson Overview
51 Computer Vision
52 Architecture of a CNN
53 Image Augmentation
54 Amending Our Model by Reverting to the Sigmoid Activation Function
55 Changing the Optimizer from Adam to SGD
56 Classifying a New Image
57 Lesson Summary

Transfer Learning and Pre-trained Models
58 Lesson Overview
59 Pre-Trained Sets and Transfer Learning
60 Fine Tuning a Pre-Trained Network
61 Classification of Images that are not Present in the ImageNet Database
62 Fine-Tune the VGG16 Model
63 Image Classification with ResNet
64 Lesson Summary

Sequential Modeling with Recurrent Neural Networks
65 Lesson Overview
66 Sequential Memory and Sequential Modeling
67 Long Short-Term Memory – LSTM
68 Predict the Trend of Apple’s Stock Price Using an LSTM with 50 Units (Neurons)
69 Predicting the Trend of Apple’s Stock Price Using an LSTM with 100 Units
70 Lesson Summary