SECTION ONE Artificial intelligence Contents • 1 History • 2 Goals 2 1 Reasoning, problem solving 2 2 Knowledge representation 2 3 Planning 31 2 4 Learning 2 5 Natural language processing 2 6 Perception 2.7 Motion and manipulation 2.8 Social intelligence 2.9 Creativity 2.10 General intelligence • 3 Approaches 3.1 Cybernetics and brain simulation 3.2 Symbolic • 3.2.1 Cognitive simulation • 3.2.2 Logic-based • 3.2.3 Anti-logic or scruffy • 3.2.4 Knowledge-based 3.3 Sub-symbolic • 3.3.1 Embodied intelligence • 3.3.2 Computational intelligence --., 3.5 Integrating the approaches • 4 Tools • 4.1 Search and optimization 4.2 Logic 4.3 Probabilistic methods for uncertain reasoning • 4.4 Classifiers and statistical learning methods • 4.5 Neural networks • 4.6 Deep feedforward neural networks o 4.7 Deep recurrent neural networks o 4.8 Control theory o 4.9 Languages o 4.10 Evaluating progress 5 Applications 5.1 Competitions and prizes 5.2 Healtcare 5.3 Automotive 5.4 Finance 5.5. Video games 5.6 Agriculture 5.7 Call Centre 5.8 CEM 5.9Energy and mining 5.10 IP 511 IT Services 5,12 Technical SuPPod 5,13 Retail • 5,14 Software, development • 8 Platforms • 6,1 Partnership on Al • 7 Philosophy and ethics 7.1 The limits of artificial general intelligence 7,2 Potential risks and moral reasoning • 7.2.1 Existential risk • 7.2.2 Devaluation of humanity • 7.2,3 Human Labour • 7,2.5 Machine ethics • 72.6 Malevolent and friendly Al 7.3 Machine Consciousness /sentience • 7.3.1 Consciousness • 7.3,2 Computationalism / functionalism 130 • 7.3,4 Robot rights 7.4 Super intelligence • 7.4,1 Technological singularity • 7.42Transhumanism • • 8 References 7,4.3 The Future of Al in marketing SECTION TWO MACHINE LEARNING Contents . t Overview 1 1 Types of problems and tasks • 2 History and relationships to other fields - 2.1 Relation to statistics . 3 Theory • 4 Approaches - 4 1 Decision tree learning - 4 2 Association rule learning 4.3 Artificial neural networks - 4.4 Deep learning - 4.5 Inductive logic programming 4.6 Support vector machines = 4.7 Clustering = 4.8 Bayesian networks = 4.9 Reinforcement learning 4.10 Representation learning = 4.11 Similarity and metric learning = 4.12 Sparse dictionary learning • 4.13 Genetic algorithms • 4.14 Rule-based machine learning • 4.14.1 Learning classifier systems • 5 Applications • 6 Model assessments • 7 Ethics • 8 Software • 8.1 Free and open-source software • 8.2 Propriety software with free access • 8.3 Proprietary software • 9 Author Comment 10 Bibliography and Reading.