Intelligent Agents

Learning Outcomes:

• Develop the understanding of key concepts of agent-based computing.
• Understand the trends that led to the rise of agent-based technologies.
• Explore the impact of these trends on the wider computing landscape.
• Learn how agents interact with their environment and with each other.
• Identify examples of agent-based systems and their applications.
• Compare different types of agent-based systems and evaluate their strengths and weaknesses.

Collaborative Discussion 1: Agent Based Systems

Learning Outcomes:

• Define and use key terms and symbols in first-order logic.
• Explain the connection between first-order logic and natural language.
• Apply quantifiers correctly within first-order logic expressions.
• Understand the core principles and structure of first-order logic.
• Construct and reason with statements using first-order logic.

Collaborative Discussion 1: Agent Based Systems

Learning Outcomes:

• Understand the historical development of agent-based systems and research.
• Critically evaluate various agent architectures and their respective strengths.
• Analyse worked examples to understand how different architectures function in practice.
• Select and justify an appropriate agent architecture for specific tasks or scenarios.
• Explain key concepts within agent theory, including the distinction between intentions and desires.

Collaborative Discussion 1: Agent Based Systems

Learning Outcomes:

• Explore the use and structure of hybrid agent architectures.
• valuate the potential benefits and limitations of hybrid approaches compared to alternative architectures.
• Critically assess different agent architectures based on their design and application.
• Justify the choice of an appropriate architecture to address specific problems or scenarios.

Team Project colleagues:

Learning Outcomes:

• Understand the key concepts of speech acts and speech act theory in the context of agent communication.
• Explain the role of ontologies in enabling meaningful communication between agents.
• Describe the purpose and structure of agent communication languages (ACLs).
• Develop and apply ontologies to support agent-based systems.
• Design and implement inter-agent communication using appropriate communication languages.

Collaborative Discussion 2: Agent Communication Languages

Learning Outcomes:

• Design agent communication using KQML, KIF, or similar languages.
• Evaluate the strengths and limitations of different agent communication languages.
• Compare and assess various approaches to agent communication.
• Create structured dialogues between agents using appropriate communication protocols.
• Understand how ontologies support knowledge sharing in agent-based systems.
• Apply ontologies effectively to enable semantic communication between agents.

Collaborative Discussion 2: Agent Communication Languages

e-Portfolio Element:

Learning Outcomes:

• Understand the key concepts and principles that underpin Natural Language Processing (NLP).
• Compare different approaches used in NLP system development.
• Explore current technologies that support the development of NLP applications.
• Evaluate the challenges involved in building and deploying NLP systems.
• Demonstrate an understanding of the core principles behind NLP technologies.

Collaborative Discussion 2: Agent Communication Languages

Learning Outcomes:

• Understand and explain the core components of Natural Language Processing (NLP) models.
• Apply the Word2Vec model to practical NLP tasks.
• Create and interpret constituency-based parse trees.
• Work through common NLP techniques using applied examples to reinforce understanding.

e-Portfolio Element:

Learning Outcomes:

• Understand the core principles and functionality of adaptive algorithms.
• Explain the fundamental concepts of artificial neural networks.
• Evaluate the strengths and limitations of emerging adaptive technologies.
• Identify new opportunities and applications enabled by these technologies.
• Critically appraise the relative advantages of adaptive techniques in various contexts.

Collaborative Discussion 3: Deep Learning

Learning Outcomes:

• Explore emerging applications of deep learning.
• Identify key ethical and social issues in deep learning.
• Investigate future developments in deep learning.
• Recognize current limitations of deep learning technologies.
• Evaluate the ethical and socio-economic impact of deep learning tools.
• Understand the role of data in deep learning systems.

Collaborative Discussion 3: Deep Learning

Learning Outcomes:

• Explain the concept of Industry 4.0 and smart manufacturing.
• Describe the characteristics of a smart shop floor and identify associated challenges.
• Analyse the application of agent-based modelling in the financial sector.
• Apply relevant concepts and theories to real-world scenarios across various sectors.
• Demonstrate an understanding of how technology can be leveraged to improve operational efficiency.
• Critically evaluate the advantages and limitations of emerging technological approaches within specific contexts.

Collaborative Discussion 3: Deep Learning

Development Individual Project: Presentation

Learning Outcomes:

• Explore emerging trends and future directions in intelligent technologies.
• Discuss the possible impacts and consequences of technological advancements.
• Consider how technology is likely to evolve in the near and distant future.
• Appraise current intelligent technologies and their capabilities.
• Assess how existing technologies may develop over time.
• Evaluate the ethical and social implications associated with the advancement of intelligent technologies.

Individual e-Portfolio Submission:

Professional Skill Matrix and Action Plan :