From Neurons to Language Models: How AI Learns
Details
🎟️ Please RSVP here to join-in for this conversation in-person.
From Neurons to Language Models: How AI Learns
Large AI models are now part of everyday technology, yet the way they actually learn remains hidden behind layers of abstraction. This talk explores the training pipeline behind modern AI from a developer’s perspective, with an emphasis on building mechanical sympathy for how these systems behave under the hood.
The discussion begins with the fundamentals of model learning — how neural networks extract patterns from data and how training gradually shapes model behavior.
With that foundation, the session moves through the major learning paradigms used in machine learning and leads into reinforcement learning, a technique that has become central to shaping modern large language models (LLMs).
Particular attention is given to Reinforcement Learning from Human Feedback (RLHF), which has often proven more effective than traditional supervised fine-tuning when guiding model behavior. The talk also introduces the intuition behind RL training, including policies as a decision layer, how policy updates influence a language model, and how such systems are evaluated and refined before deployment.
The goal is to develop a clear, end-to-end understanding of how the field evolved — from training basic neural networks to building the large language models that power today’s AI systems — and how a deeper understanding of their internals can help developers use them more effectively.
About the speaker:
Rajshree is a seasoned full-stack developer with a passion for building clean, scalable, and simple web applications and APIs. She have designed and implemented agentic AI workflows and have hands-on experience with model selection, capabilities, and the practical use of AI tools and coding agents. She is particularly interested in understanding neural networks and how they work under the hood, and enjoy building deeper intuition around how modern AI systems learn and behave. She like developing mechanical sympathy for new technologies and regularly explore emerging ideas and tools in the evolving AI and software landscape
🎟️ Please RSVP here to join-in for this conversation in-person.