-
Building a RAG Pipeline from Scratch with Python
A hands-on walkthrough of building a Retrieval-Augmented Generation system — from document indexing to grounded LLM responses — using FAISS, sentence-transformers, and a local model.
-
Backpropagation from Scratch with NumPy
Implement a two-layer neural network with forward pass, loss computation, and backpropagation using only NumPy. No frameworks — every gradient derived and coded explicitly.
-
Text Classification for Cyberbullying Detection: A Practical NLP Walkthrough
Build a cyberbullying detection classifier from raw text to evaluation — preprocessing, TF-IDF features, SVM and Random Forest, cross-validation, and a full sklearn pipeline. Based on real research published at IEEE ACROSET 2024.
-
Explainable AI in Healthcare: TabTransformer + SHAP for IoMT Security
Apply a TabTransformer — a Transformer architecture for tabular data — to IoMT intrusion detection, then explain its predictions using SHAP. A deep dive into XAI for high-stakes healthcare systems, based on our Academic Press 2026 book chapter.
-
Google Gemini updates: Flash 1.5, Gemma 2 and Project Astra
We’re sharing updates across our Gemini family of models and a glimpse of Project Astra, our vision for the future of AI assistants.