Build a small language model from scratch: Data pre-processing

How transformer took over computer vision? CNN's struggle with long range dependency

New Series Launch | Transformers for Vision and Multimodal LLMs | Lecture 1

RLHF From Scratch - 5 hour workshop

Transformers for Vision and Multimodal LLMs | New bootcamp launch

Production Level RAG Workshop: Part 2

Build and deploy Computer Vision Model for fall detection | Roboflow + Streamlit | Physical Safety

Simple Demo: Google's NotebookLM from Scratch

Machine Learning in Production | How Docker helps in Deployment

Computer Vision Bootcamp | Full 12 hour series | OpenCV, RCNN, UNet, YOLO and Roboflow

How the VLLM inference engine works?

Roboflow - Best way to build end-to-end computer vision pipeline

Production level RAG Workshop: Part 1

Let us build GPT-OSS from Scratch

YOLO + OCR for License Plate Recognition | Computer Vision Hands-on Project

A beginners introduction to YOLO | You Only Look Once | Computer Vision

Lecture 4 - Policy Gradient Methods from Scratch | Hands-on Reinforcement Learning

Lecture 3 - Deep Q Networks | Hands-on Reinforcement Learning

I pre-trained Gemma3 270M from scratch

Build a small language model from scratch: Pre-training and Inference

UNet and its Family: UNet++, Residual UNet, and Attention UNet | Computer Vision Bootcamp

Lecture 2 - Three Pillars of Classical Reinforcement Learning| Hands on Reinforcement Learning

UNet: the 2015 model with 118k+ citations that changed segmentation - And how GenAI brought it back

AI Agent Bootcamp (Full Course) - Learn Smolagents, LangGraph, CrewAI, n8n | By MIT PhD

DynaRoute: Vizuara's AI Router That Cuts LLM Costs by 70% While Maintaining Performance

Introduction to Mask R-CNN for image segmentation | Computer Vision bootcamp

Hands on Reinforcement Learning - Lecture 1

Machine Learning in Production | How to write Modular Code

Object Detection using R-CNN, Fast R-CNN, and Faster R-CNN | Computer Vision Hands-on Bootcamp

Object tracking and Counting | OpenCV + YOLO | Computer Vision Hands-on bootcamp

Launch of GPT-OSS: OpenAI's first open source model after GPT-2

Lecture 22 -Blueprint for building Large Reasoning Models | DeepSeek-R1| Reasoning LLMs from Scratch

Hands on Computer Vision Bootcamp | Day 1

3-in-1 LIVE hands-on bootcamps | Language, Reasoning, Vision

Lecture 21 - Build your first Reasoning Model using GRPO | Reasoning LLMs from Scratch

Machine Learning in Production | How CRED Built a Cred-ible ML System

Build Small Language Model (SLM) from scratch | 3 day LIVE bootcamp by MIT PhD

Hands-on Reinforcement Learning Bootcamp [LIVE] by Purdue PhD

Hands-on Computer Vision Bootcamp [LIVE] by MIT PhD

Hands on Computer Vision Bootcamp [LIVE] | By MIT PhD

Lecture 20 -GRPO |Reinforcement Learning Phase|Reasoning LLMs from Scratch

AI Hands-On interactive courses for school students [grades 1-10] | By MIT, Purdue PhDs

AI high school research program [grades 8-12] | By MIT, Purdue PhDs

Build a Gesture Controlled Game in Scratch Using Teachable Machine (No Coding Required!)

Coding a Vision Transformer from scratch using PyTorch

Minor in AI by MIT PhDs

Generative AI Minor by MIT PhDs

Lecture 19 - Applying RL in LLMs | Reinforcement Learning Phase | Reasoning LLMs from Scratch

Hands on Reinforcement Learning Bootcamp

Introduction to Vision Transformer (ViT) | An image is worth 16x16 words | Computer Vision Series

Machine Learning in Production | What Swiggy Teach Us About Better ML Communication

GRPO Explained under 40 Minutes

A Historical Journey through CNNs and Modern Computer Vision 2010–2025 | Computer Vision Series

A visual guide to Word Embeddings

Lecture 18 - Proximal Policy Optimization|Reinforcement Learning Phase | Reasoning LLMs from Scratch

From Classrooms to the World: AI Courses for Students Grades 1-12 | By MIT, Purdue PhDs

Build a Smart AI Event Scheduler with N8N + GPT + Slack + Google Calendar (No Code!)

High schoolers can also publish AI research. Here is how | By MIT, Purdue PhDs

Use Neural Network to find a good CNN Architecture - NASNet | Computer Vision Series

Lecture 17 - TRPO Solution Methodology | Reinforcement Learning Phase | Reasoning LLMs from Scratch