Main Page

Welcome to Marovi — a collaborative knowledge base for mathematics, machine learning, and multilingual education.

Recently updated

• Word Embeddings
• Transfer Learning
• Stochastic Gradient Descent
• Softmax Function
• Recurrent Neural Networks
• Overfitting and Regularization
• Neural Networks
• Loss Functions
• Linear Regression
• Gradient Descent

Browse by topic

Machine Learning Core concepts, algorithms, and techniques for learning from data.	Deep Learning Neural network architectures, training techniques, and modern methods.
Natural Language Processing Text understanding, language models, and NLP methods.	Optimisation Algorithms and methods for training machine learning models.
Statistics Statistical foundations, probability, and inference methods.

Browse by type

• Research Papers — Articles about notable publications in ML and AI
• Summaries — Concise overviews of articles and papers

Notable papers

• Attention Is All You Need (2017) — The Transformer architecture
• BERT Pre-training of Deep Bidirectional Transformers (2019) — Bidirectional pre-training for NLP
• Language Models are Few-Shot Learners (2020) — GPT-3 and in-context learning
• Deep Residual Learning for Image Recognition (2016) — ResNet and skip connections
• Generative Adversarial Nets (2014) — The GAN framework

About Marovi

Marovi aims to make technical knowledge accessible across languages. Our content is enriched through AI-assisted translation and quality pipelines, ensuring accurate and readable articles in multiple languages.

Getting started

• Browse articles by category
• Recent changes
• All pages