MLOps World: Machine Learning in Production Courses

Explainable Forecasting through Causal Inference

Discover a novel causal model for multivariate time series forecasting using Xi-Correlation and Dynamic Conditional Correlation methods to detect causal relationships and predict outcomes.

• YouTube
• 25 minutes
• Self-Paced
• Free Video

From Executives' Delusions to Making AI Enablement a Reality - Bridging Data Readiness Gap

Discover how to bridge the critical data readiness gap that prevents successful AI implementation, with practical frameworks for assessment and actionable strategies.

• YouTube
• 32 minutes
• Self-Paced
• Free Video

Machine Learning for Machine Uptime - AI-Powered Fault Detection and Predictive Maintenance

Discover AI-driven predictive maintenance for medical devices, covering time-series modeling, anomaly detection, ML techniques, FDA guidelines, and real-world applications to reduce downtime.

• YouTube
• 26 minutes
• Self-Paced
• Free Video

Optimizing NLP Workflows by Combining GenAI and Traditional LLMs

Discover how to optimize NLP workflows by combining generative AI with traditional models like BERT for efficient data labeling, text clustering, and scalable insights extraction.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Building with GenAI - What It Really Takes to Get Bots into the Wild

Discover practical challenges of deploying GenAI bots in production, from prompt engineering to cost management, with real-world insights from a national media platform deployment.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Generative AI for Retail - Personalization with Diffusion Models

Explore how diffusion models revolutionize retail by generating personalized product images on demand, reducing costs and accelerating content creation for enhanced shopping experiences.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Scaling Ultra Low Latency LLM Inference

Discover techniques for scaling ultra-low latency LLM inference, covering model optimization, KV caching, specialized hardware requirements, and routing architectures for production.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

GARAGe - How ADA Uses LLMs to Make Retrieval Smarter

Discover how GARAGe flips RAG by using generation to improve retrieval, creating smarter AI agents with better context ranking and reduced hallucinations for production systems.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Ensuring Data Security in the AI Revolution

Discover strategies for securing AI pipelines and protecting sensitive data from preparation through deployment, covering database protection, leak detection, and regulatory compliance.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Scaling of Quantized Large Language Models for Efficient Inference

Discover how quantization affects large language model scaling and develop empirical laws for efficient LLM inference deployment through theoretical insights and practical compression techniques.

• YouTube
• 33 minutes
• Self-Paced
• Free Video

Towards World Models and General Agents

Discover how foundation world models like Genie 2 and reinforcement learning are paving the path toward general AI agents capable of reasoning, acting, and self-improving across diverse domains.

• YouTube
• 25 minutes
• Self-Paced
• Free Video

Uncovering Financial Fraud with Graph Machine Learning at Scale

Discover how graph machine learning transforms fraud detection by analyzing entity relationships and coordinated suspicious activities at enterprise scale.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

LLMOps Infrastructure for Production-Grade Agentic RAG Applications with Union.ai

Master LLMOps infrastructure for production-grade agentic RAG applications using Union.ai platform, covering deployment, iteration, and best practices for maintaining AI systems.

• YouTube
• 1 hour 22 minutes
• Self-Paced
• Free Video

Scaling Down, Powering Up - Can Efficient Training Beat Scaling Laws?

Explore data-centric and model-centric strategies for training efficient language models, including small LMs, data filtering, pruning, distillation, and quantization techniques.

• YouTube
• 1 hour 9 minutes
• Self-Paced
• Free Video

Optimized RAG - Strategies for Cost and Scale

Master cost-effective RAG deployment strategies from prototype to production, covering embedding quantization, context compression, and ranking techniques with hands-on Python implementation.

• YouTube
• 1 hour 27 minutes
• Self-Paced
• Free Video