3. Software Automation

3.1. Algorithms In Machine Learning

Investigate how machine learning (ML) supports automation through the use of DevOps, robotic process automation (RPA) and business process automation (BPA)

• ML in DevOPS, RPA and BPA

• MLOps

Distinguish between artificial intelligence (AI) and ML

• Artificial Intelligence and Machine Learning

Explore models of training ML

• Types Of Machine Learning Summary

Including

supervised learning

• Supervised vs Unsupervised Learning

unsupervised learning

• Supervised vs Unsupervised Learning

• Unsupervised Learning: Clustering

• Extension: The K-means Clustering Algorithm

• Extension: Building a K-means Clustering Model

semi-supervised learning

• A Semi-Supervised Model

• Random Forests

• Semi-Supervised Learning and Random Forests

reinforcement learning

• Reinforcement Learning

Investigate common applications of key ML algorithms

Including

data analysis and forecasting

• Exercise: Applications of Machine Learning Algorithms

Select examples:

• Predicting student marks using a multiple linear regression model: Multiple Linear Regression

• Predicting whether it will rain or not using a logistic regression model: Predicting With A Logistic Regression Model (code challenge)

• Predicting prices using a regression tree: Extension: Building and Predicting With A Regression Tree

virtual personal assistants

• Exercise: Applications of Machine Learning Algorithms

Example:

• Google AI: How Patterns in Human Behaviour Influence ML and AI Software Development (19:30 into the video Artificial intelligence and its ethics | DW Documentary 2020)

image recognition

• Exercise: Applications of Machine Learning Algorithms

Examples:

• Classifying digits using KNN classification: Extension: Image Data, Extension: Building a KNN Classification Model (code challenge)

• Classifying digits using a neural network: Building a Neural Network For Classification (code challenge), see also More Advanced Neural Networks > Convolution Neural Networks

Research models used by software engineers to design and analyse ML

Including

decision trees

• Decision Trees

• Building a Classification Tree

• Classifying With a Classification Tree

• Node Impurity and Tree Height

• A Semi-Supervised Model

• Random Forests

• Extension: Building a Classification Tree

• Extension: Interpreting The Output Graph

• Extension: Predicting With a Classification Tree

• Building a Regression Tree

• Predicting With a Regression Tree

• Extension: Building and Predicting With A Regression Tree

• Semi-Supervised Learning and Random Forests

• Interpreting Decision Trees

neural networks

• Deep Learning

• Neural Networks

• RGB to Hue and Saturation

• Information Flow: Making a Prediction

• Calculating Errors

• Training a Neural Network

• Problem and Model Analysis

• Neural Networks for Classification

• More Advanced Neural Networks

Describe types of algorithms associated with ML

Including

linear regression

• Linear Regression

• Measuring Error

logistic regression

• Logistic Regression

• Measuring Error

K-nearest neighbour

• KNN Regression 1D

• Visualising KNN Regression 1D (k = 1)

• Extension: Visualising KNN Regression 1D (k = 2)

• KNN Regression 2D

• Extension: Building a KNN Regression Model

• Extension: Selecting The Value of k

• KNN Classification

• Extension: Image Data

• Extension: Building a KNN Classification Model

3.2. Programming For Automation

Design, develop and apply ML regression models using an OOP to predict numeric values

Including

linear regression

• Fitting a Linear Regression Model

• Plotting Functions and Visualising Models

• Making Predictions

• Measuring Error Using the MSE

• Extension: Fitting The Model

• Multiple Linear Regression

polynomial regression

• Polynomial Regression

• The Relationship Between Linear Regression and Polynomial Regression

• Building a Polynomial Regression Model

• Extension: Selecting The Polynomial Degree

logistic regression

• Building a Logistic Regression Model

• Predicting With A Logistic Regression Model

• Extension: Further Classification Metrics

• Extension: Multiple Logistic Regression

Apply neural network models using an OOP to make predictions

• Building a Neural Network for Regression

• Building a Neural Network For Classification

3.3. Significance And Impact Of ML And AI

Assess the impact of automation on the individual, society and the environment

Including

safety of workers

• The Impacts of Automation on the Individual, Society and the Environment

people with disability

• The Impacts of Automation on the Individual, Society and the Environment

the nature and skills required for employment

• The Impacts of Automation on the Individual, Society and the Environment

production efficiency, waste and the environment

• The Impacts of Automation on the Individual, Society and the Environment

the economy and distribution of wealth

• The Impacts of Automation on the Individual, Society and the Environment

Explore by implementation how patterns in human behaviour influence ML and AI software development

Including

psychological responses

• How Patterns in Human Behaviour Influence ML and AI Software Development

patterns related to acute stress response

• How Patterns in Human Behaviour Influence ML and AI Software Development

cultural protocols

• How Cultural Protocols and Belief Systems Impact AI

belief systems

• How Cultural Protocols and Belief Systems Impact AI

Investigate the effect of human and dataset source bias in the development of ML and AI solutions

• Bias in AI