Topics

The topics in this session include foundational elements of logic and its application in AI (specifically Horn clauses and SLD resolution), different knowledge representation schemes (production rules, frames, and literals), methods for generalization and learning within these schemes (LGG, attribute-only space search, heuristic learning, and knowledge acquisition), and approaches to handling uncertainty in expert systems. Examples from various problem domains, such as mass spectrometry, symbolic integration, chemistry, music analysis, and student modeling, illustrate the practical application of these concepts.

This session provides a comprehensive overview of artificial intelligence (AI), focusing on the evolution, concepts, and applications of Generative AI. The session explores topics such as the history of AI, different types of machine learning, neural networks, deep learning, large language models, and AI agents. It examines various generative models, including Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). The session emphasizes prompt engineering and transfer learning techniques for optimizing the performance of these models.

Retrieval-Augmented Generation (RAG) enhances generative AI by integrating external information retrieval, enabling models to produce accurate, contextually informed responses. It combines indexing, retrieval, augmentation, and generation, with semantic search playing a key role in retrieving relevant data based on meaning rather than exact keywords. By leveraging vector embeddings and similarity measures, RAG reduces hallucinations and dynamically updates knowledge without retraining the model. This approach is widely applied across industries, such as customer service, education, legal research, and content creation, to address knowledge-intensive tasks. Its implementation relies on vector databases and advancements in embedding models to efficiently connect AI systems with external, authoritative information sources.

This session covers three significant concepts and tools for development and deploment of software solutions (including AI Solutions).

The session frames agentic AI as an evolution of basic RAG for business workflows. It starts by contrasting a static RAG pipeline—query, retrieve, answer—with an AI agent that interprets goals, plans multi-step processes, chooses among tools (including RAG), and iterates based on feedback until the goal is satisfied.

This session evaluates leading Python-based agentic AI frameworks. The guide highlights LangGraph, Microsoft AutoGen, Strands Agents, and LlamaIndex as the most durable and pedagogically distinct tools for building intelligent systems. These frameworks are categorized into four schools of thought: graph-based workflows, multi-agent conversations, model-driven orchestration, and data-centric retrieval. Furthermore, the sources compare how these libraries implement core agent functions like memory, perception, and reasoning. The material also contrasts these code-first Python SDKs with visual automation platforms like n8n, while emphasizing emerging interoperability standards such as MCP and A2A.

This session explores the intricacies of prompt engineering for large language models (LLMs), emphasizing its importance in optimizing LLM performance for specific tasks. Unlike traditional machine learning models, evaluating LLMs involves subjective metrics like context relevance, answer faithfulness, and prompt relevance.

This session explores how traditional NLP techniques function as a vital foundation for modern agentic AI systems rather than being replaced by them.

This session covers integrating knowledge graphs into agentic AI systems to enhance reasoning, memory, and factual grounding. It details the construction of graphs using both traditional NLP tools like spaCy for precision and Large Language Models for semantic flexibility. The session explains how formal ontologies serve as the structural blueprint for these systems, ensuring consistent vocabulary and logical constraints.

This session focuses on one of the most practically important capabilities in generative AI engineering: getting large language models to produce output that machines can reliably consume. LLMs excel at generating fluent natural language, but the systems we build around them — databases, APIs, application backends — speak in strict, formal languages like SQL, SPARQL, and Cypher. Bridging this gap requires more than clever prompting. It demands an understanding of how token generation works, how formal grammars can constrain that generation, and how inference engines like Ollama support structured decoding at the architectural level.

(Content not yet posted. Please check back.)

(Content not yet posted. Please check back.)

(Content not yet posted. Please check back.)

(Content not yet posted. Please check back.)