TensorFlow

AI eBook

  FREE DOWNLOAD  eBook 
      size: 3.5 MB

Ver. 1.0 / 2020 
       
eBooks only for WINDOWS!

Nr.19          (no further obligation!)

BUY


AI Neuronal Network
 
The eBook with over 120 pages describes the basics of Artificial Intelligence (AI). We will start step by step so that you are not overwhelmed by the many new terms. In the end you will understand what a tensor is and how a nuronal network works.
Fuzzy Until fuzzy logic, it was thought that all processes always had to be described with high precision. With fuzzy logic we show how to describe fuzzy knowledge and use it as an example in control engineering.
Since the Internet and networked sensors we have a lot of data (Big Data) from which further information can be extracted and decisions made. Statistical methods such as regression or neural networks are used to classify the data or find internal relationships. Big Data
NN The eBook is aimed at beginners who want to program algorithms in Python with little knowledge of computer science and without much mathematics.  are not covered in this eBook!

By means of examples with PyBrain and Tensorflow in Python and with numerous pictures and animations the understaBasics of Python are not covered in this eBook!

The success of the AI is also due to the ever faster hardware. Today with special GPU and especially cloud services, complex models can be executed on faster and, above all, multiple servers (parallel computers).

Python

 

Content


Start eBook

This eBook
       Artificial Intelligence
       Data analysis
       Expert Systems
Copyright

------ Fuzzy Logic ------------------
001 right and wrong
002 Set theory
003 Mathematics
004 Membership
005 Calculating with sets
006 Calculating with sets
007 Small and large people sharp
008 Small and large people fuzzy
009 Fuzzy membership
010 Fuzzy Complement
011 Fuzzy average (AND)
012 Fuzzy union (OR)
013 laws of set theory
014 The sentence of the excluded third party
015 Strange statements!
016 Truth and falsehood
017 Relations
018 Probability
019 Possibility

------ Fuzzy control ---------------
020 What is a controler?
021 Shower temperature
022 Fuzzy water temperature
023 Linguistic variables
024 Rule base
025 Output membership functions
026 Complete the rule basis
027 Inference
028 Aggregation
029 Implication
030 Accumulation
031 Centre of gravity method
032 Characteristic curve
033 Linear and non-linear
034 2 input variables and one output
035 Aggregation and Implication
036 Accumulation
037 Defuzzyfie Singletons
038 3-D map
039 Advantages of the fuzzy maps

---- Neuronal Networks -------------
040 Introduction
041 The Brain
042 The brain and its performance
043 The network
044 Neurons
045 The neuron and synapse
046 Learning
047 The artificial elements
048 Function of the artificial elements
049 Example XOR function
050 Example XOR function
051 Separability
052 How does a human learn?
053 Supervised learning
054 Linear and non-linear transfer function
055 How do you change the weights?
056 Backpropagation Lernmethode
057 Learning rate
058 Local and global minima
059 Learning without teachers
060 Networks topolgy

---- Application neural networks --------
061 Introduction
062 Identification of a controlled system
063 Example Identification
064 Training and validation data
065 State space and standardization
066 Termination threshold for the learning process
067 Autonomous driving
068 NN learns to drive a truck backwards
069 Data analysis
070 Diagnosis and prognosis
071
Data Mining and Big Data

--- Machine learning with PyBrain --------
072 What does Machine Learning mean?
073 NN is learning
074 Supervised NN in PyBrain
075 Supervised NN in PyBrain
076 Supervised Learning algorithm
077 Backpropagation is active
078 How to use a network?
079 More training is better?
080 Is more training better?
081 More neurons?
082 More neurons?
083 Overloading
084 Increase input-output
085 More neurons!
086 Learning rates and weights
087 Momentum!
088 Saving the weights
089 Why normalize to 0 and 1?
090 Learning until a threshold is reached
091 More data
092 Random data between 0 and 1
093 Two inputs and one output
094 From regression to classification
095 Classification with neural networks
096 Classification = the result
097 Sequential data type

--- NN with TensorFlow -------------------
098 TensorFlow
099 Simple example
100 Simple Example Overview
101 MNIST pictures
102 Datasets at TensorFlow
103 Load pictures
104 Normalizing Images
105 Building a neural network
106 First layer
107 Hidden layer
108 Dropout Layer
109 Output layer
110 NN Block diagram
111 Compile Model
112 Cost function
113 Metrics
114 NN learns
115 NN test
116 NN run in Browser
117 NN run in SPYDER
118
Parallel computer and cloud

---- Genetic Algorithms -----------
119 What does optimization mean?
120 Charles Darwin
121 Evolutionary Algorithms
122 Genetic Algorithms
123 Genetic coding in nature
124 Functional Genetic Algorithms
125 Coding of the parameters
126 Population
127 Fitness Function
128 Optimization procedure
129 Selection
130 Modification of genetic information
131 Crossover
132 Mutation
133
Offspring and the next generation

----- Chaos Theory ---------------------
134 Introduction
135 Weather Forecast
136 Prediction and determinism
137 Feigenbaum-Diagram
138 The Lorenz water wheel

---------- THE END --------------------------

 





 


email@ebookaktiv.de


2003-2020
    ebooksmechatronic.com

Last Update: 02.04.2020


5 Euro

--------------
eBooks      prices
--------------

  1     5,0€
  3   10,0€

  6   15,0€
  9   20,0€

ALL download
30,0€
ALL on CD
35,0€
(Germany+Europe)

--------------
      

Example

Pages

seee

below

in content

LINKS   

 

 

 

 

NN

AI

euron

rtificial

ntelligence