-
Enhancing decision making with RAG chatbot
Description AI powered virtual assistant speacialized in the AltA methodology (Alternative Analysis) of NATO. It combines Large Language Models (langchain, groq) with Retrieval Augmented Generation (Chroma) to provide responses to specific questions related with the topic that “general purpose” models cannot provide.
Read more… -
Prototype-based learning. Part II: LVQ family of models in PyTorch
Description In my journey to bridge psychology and data science, I discovered Learning Vector Quantization (LVQ) and immediately saw its potential connection to human category learning. This realization led me to dive deeper, implementing LVQ from scratch, initially by coding all the operations using PyTorch, and then by abstracting the optimization and learning processes to fully leverage PyTorch’s features.
Read more… -
Prototype-based learning. Part I: GMLVQ from scratch
Description In my journey to bridge psychology and data science, I discovered Learning Vector Quantization (LVQ) and immediately saw its potential connection to human category learning. This realization led me to dive deeper, implementing LVQ from scratch, initially by coding all the operations using PyTorch, and then by abstracting the optimization and learning processes to fully leverage PyTorch’s features.
Read more…