Teaching Demonstrations

Interactive classroom-ready activities for learning computer science and AI concepts through direct manipulation, visual feedback, and concrete examples.

Demonstrations for Discrete Mathematics

A polished interactive graph theory activity comparing Eulerian Circuit and Hamiltonian Cycle. Students animate edge traversal, vertex visitation, Eulerian degree characterization, Hamiltonian backtracking, and the growth of search states.

Discrete mathematics Graph theory Eulerian circuit Hamiltonian cycle NP-completeness Algorithmic characterization

Rules of Inference Interactive Lab

A vibrant classroom lab for propositional logic. Students reveal all eight inference rules progressively, study concrete examples, and arrange proof steps through drag-and-drop practice.

Discrete mathematics Propositional logic Modus ponens Modus tollens Transitivity Counterexamples

Prompt Geometry Visualizer

A browser-based version of the prompt engineering visualization. It shows prompt growth as a trajectory through an embedding-like semantic universe, with anchor concepts, numbered prompt states, semantic rings, and gender-direction vectors.

Prompt engineering Embeddings Semantic space Vector directions AI literacy

AI Foundations: Three Guided Mini Labs

A Module 1 sequence for explaining the AI family, neural network learning, and LLM generation through interactive, academically grounded classroom visuals.

AI vs ML vs Deep Learning Generative AI LLMs Neural network learning Timeline of AI Hallucination

Custom GPTs Teaching Visual

A polished interactive visual for explaining how a general ChatGPT conversation becomes a purpose-built teaching assistant through clear purpose, instructions, knowledge, examples, rules, tools, testing, and refinement.

Custom GPTs Teaching assistants Reusable workflows Instructions Guardrails Refinement

CNN Convolution Activity

A standalone interactive demonstration for convolutional neural networks. It begins with a 1D cricket speed-gun convolution example, then moves into image filters, feature maps, stride, padding, output shape, 3D inputs, and pooling.

Convolution Image filters Stride Padding Pooling CNN shape logic

Contact for workshops and collaborations

For FDPs, keynotes, classroom demonstrations, workshops, and research discussions, connect with Dr. Mahipal Jadeja, Assistant Professor at MNIT Jaipur. Email: mahipaljadeja.cse@mnit.ac.in.