Hands-On Machine Learning with Auto-Keras

Hands-On Machine Learning with Auto-Keras
Hands-On Machine Learning with Auto-Keras
English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 2h 40m | 446 MB

Develop state-of-the-art machine learning models with just a few lines of code!

If you want to build efficient models using the open-source Auto-Keras library, then this course is perfect for you. It will teach you how to use Auto-Keras to build custom machine learning and AI models effectively, even with limited machine Learning knowledge.

You will learn how to train a network automatically and evaluate it using Auto-Keras. You will begin by installing Auto-Keras and using it to implement basic algorithms. You will then train more advanced models as you progress to state-of-the-art techniques.

By the end of the course, you will be confident about using Auto-Keras to build custom machine learning models for your organization.

Learn

  • Visualize how Auto-Keras works by learning some of its best-performing architectures
  • Achieve state-of-the-art Convolutional Neural Network performance in realistic scenarios and with very little development time
  • Improve performance on text-based tasks involving classification and regression
  • Obtain production-ready models with Auto-Keras on sentiment analysis tasks
  • Leverage pre-trained models in Auto-Keras to save time by writing less code and by not doing any model training
  • Generate your own datasets in order to estimate how well Auto-Keras performs in complex conditions
  • Learn how to build and make predictions and your own data sets
  • Learn the basics of deploying a model
Table of Contents

Getting Started with Auto-Keras
1 The Course Overview
2 The Need for Auto-Keras
3 Installing Auto-Keras
4 The MNIST Data Set
5 An Auto-Keras Classifier for MNIST
6 Making Predictions on Our Own Data

Artificial Neural Network Models
7 ANN Generation
8 ANN Classifier for Identifying Handwritten Digits
9 ANN Model for Predicting House Prices
10 Visualizing the Best ANN
11 Exploring More Data Sets

Convolutional Neural Network Models
12 CNN Generation
13 CNN Classifiers for Identifying Handwritten Digits
14 CNN Classifiers for Identifying Other Objects
15 CNN Regressor for MNIST
16 Visualizing the Best CNN

Text Classification and Regression
17 Text-Based Tasks
18 Text Classification for Reuters News
19 Text Classification for Spam Filtering
20 Text Regression on a Real-World Data Set
21 Generating Our Own Data Set

Sentiment Analysis
22 Sentiment Analysis Basics
23 Auto-Keras’ Pretrained Models for Sentiment Analysis on a Real-World Data Set
24 The Pretrained Models on Some of Our Own Data
25 Auto-Keras Classifier for Sentiment Analysis
26 Auto-Keras Regressor for Sentiment Analysis

Object Detection
27 Object Detection Basics
28 Using Auto-Keras’ Pretrained Models for Object Detection
29 Building Our Own Data Set for Use with the Pretrained Model
30 Deploying a Model

Topic Classification
31 Basics of Topic Classification
32 Using Auto-Keras’ Pretrained Models for Topic Classification
33 Building Our Own Dataset for Use with the Pretrained Model
34 Our Own Auto-Keras Model for Topic Classification