INNFEG – Implementing Neural Networks for E-Governments

The Course Name: INNFEG – Implementing Neural Networks for E-Governments

The Duration: 5 Days

The Overview:

The purpose of this course is to teach participants how to design and implement e- Government solutions via neural networks, deep learning and Python v3.0

What You Will Learn:

• The infrastructure of E-Government.
• Data and Data Mining
• Deep Learning and Neural Networks
• Neural Networks and Python
• The classification of E-Governments and the relation with Neural Networks.
• E-Government Performance Assessment Based on Neural Network
• Neural Networks Approach for Monitoring and Securing the E-Government Information Systems

The Course  Index:

Day 1

Module 1) The infrastructure of E-Government.

The Introduction

Course index and Daily plan explanations.

Meeting with students about their experience and expectation.

Explaining students the outcome of the course

1.1 What is E-Government

1.2 The Scope of E-Government

1.3 Databases

1.4 Biometrics, identification and verification

1.5 Usability and accessibility

1.6 E-Government: Other views

Module 2) Data and Data Mining

2.1 The definition of Data Mining and analysis

2.2 How to define the problem

2.3 Data Requirements

2.4 Data Mining Algorithms

Day 2

Module 2 Data and Data Mining continues

2.5 The prerequisites of Data

2.5.1 The Data Mining prerequisites

2.5.2 The Algorithm prerequisites

2.5.3 The Software prerequisites

2.6 Data Reduction

2.6.1 The Goals

2.6.2 How to use Data

2.6.3 Data Reduction in Python

2.7 Clustering

2.7.1 The Goals

2.7.2 How to cluster Data

2.7.3 Clustering in Python

2.8 Classification

2.8.1 The Goals

2.8.2 How to make the classification of the Data

2.8.3 classification in Python

2.9 Anomaly Detection

2.9.1 The Goals

2.9.2 Anomaly Detection of the Data

2.9.3 Anomaly detection in Python

Day 3

Module 3) Deep Learning and Neural Networks

3.1 What is Deep Learning

3.2 What is Neural Networks

3.3 What is convolutional Neural Networks

3.3.1 The Architecture

3.3.2 Convolutional layer

3.3.3 Pooling layer

3.3.4 Dense Layer and classification

3.3.5 Deep CNNs

3.4 Advanced Cases

3.4.1 Natural Language processing

3.4.2 Image/Video processing    

3.5 Traditional Architectures

3.6 Siamese Networks

3.7 Dense Predictions

3.8 Localization, Detection and Alignment

Day 4

Module 4) Neural Networks and Python

4.1 Lasagne and nolearn

4.2 Loading the MNIST dataset

4.3 ConvNet Architecture and Training

4.4 Prediction and Confusion Matrix

4.5 Filters Visualization

4.6 Theano layer functions and Feature Extraction

Module 5) The classification of E-Governments and the relation with Neural Networks.

5.1 The Introduction

5.2 The Bounded Rationality Approach

5.3 The Neural Networks Methodology

5.4 The classification of the Government

5.5 The conclusion

Day 5

Module 6) E-Government Performance Assessment Based on Neural Network

6.1 The Establishment of Government Peformance Assesment Index System

6.2 The Assesment Based on BP Neural Network

6.3 The Feasibility of BP Neural Network Used in Government Performance

6.4 The Network Detecting

6.5 The Conclusion

Module 7) Neural Networks Approach for Monitoring and Securing the E-Government Information Systems

7.1 The Introduction

7.2 The Neural Networks Model

7.3 The Conclusion