Aligning Language Models with LESS Data and Simple Preference Optimization (SimPO)
Discover innovative approaches to language model alignment through LESS data selection and SimPO optimization, achieving superior performance with reduced computational resources and simplified objectives.
Pix2Pix Implementation From Scratch
Learn to implement Pix2Pix from scratch, covering discriminator and generator models, dataset loading, and training. Gain hands-on experience in building this powerful image-to-image translation algorithm.
Easy Hand Sign Detection - American Sign Language ASL - Computer Vision
Learn to detect American Sign Language hand signs using computer vision techniques, from setup to customization, with practical coding examples and hands-on training.
Building a State-of-the-Art Open-Source Model - DBRX Development Story
Discover the journey behind DBRX, Databricks' open-source foundation model. Learn tools, methods, and insights for building high-quality LLMs, with real-world examples and best practices from the development team.
Exploring MLOps and LLMOps - Architectures and Best Practices
Dive into MLOps and LLMOps architectures, components, and best practices. Learn strategies for efficient implementation and improved model performance in this comprehensive technical session.
Deep Learning with Noisy Labels
Explore techniques for training deep learning models with noisy labels, addressing challenges in data collection and annotation across various domains, including medical imaging.
Challenges of Federated and Zero-Cost Neural Architecture Search
Explore advanced neural architecture search techniques, focusing on federated settings and zero-cost searching algorithms through weight sharing and efficient subnet discovery methods.
Vertex AI Workshop - Training, Serving, and Pipelines
Explore hands-on Vertex AI for ML model training, serving, and pipeline creation. Learn to leverage Google Cloud's powerful tools for efficient machine learning workflows and deployments.
Powering Llama 3 - A Peek into Meta's Massive Infrastructure for Generative AI
Dive into Meta's advanced infrastructure powering Llama 3, exploring the technological backbone and innovative systems behind their next-generation generative AI development.
How to Deploy Machine Learning Models in Production
Learn to train, deploy, and maintain machine learning models in production environments, covering real-time decision-making and scalable frameworks for experimentation and deployment.
Small but Mighty: Subset Selection and Knowledge Distillation
Explore cost-efficient AI training methods, focusing on subset selection and knowledge distillation techniques to address challenges in large language model development.
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Explore a novel fine-tuning method for Large Language Models that improves performance without additional human-annotated data, using self-play mechanisms and theoretical guarantees.
Federated Learning: Unlocking the Value of Distributed Data
Explore federated learning to leverage distributed data for robust machine learning models without centralizing sensitive information. Learn benefits, challenges, and practical applications.
The Myth of AI Breakthroughs - Cutting Through Hype in Neural Network Research
Explore AI realities, efficient model training, and cutting-edge research with Jonathan Frankle. Gain insights on facial recognition, the lottery ticket hypothesis, and navigating AI hype.
The Art and Science of Training Large Language Models
Explore challenges and strategies in training large language models with insights from MosaicML experts. Gain practical knowledge on model optimization, data complexities, and efficient AI development.
Azure ML: Python SDK v2 - Creating Machine Learning Applications
Develop ML applications using Azure Machine Learning Studio Python SDK v2. Train models and publish to Azure ML model repository.
Creating a Bernie Sanders Detector Using YOLOv4 - OpenCV Python - Computer Vision
Learn to create a Bernie Sanders detector using YOLOv4/v5, OpenCV, and Roboflow. Build datasets, train models, and implement real-time detection on various platforms.
From Concept to Production - Template for the Entire Machine Learning Journey
Develop a production-ready ML pipeline from concept to deployment, covering data prep, model training, and orchestration using Kubeflow on Google Cloud Platform's Vertex AI.
Democratizing AI Model Training on Kubernetes with Kubeflow TrainJob and JobSet
Discover how to streamline AI model training on Kubernetes using Kubeflow TrainJob API and JobSet, enabling efficient distributed training and LLM fine-tuning with simplified Python workflows.
Improving Model Robustness with Natural Language Corrections
Explore techniques for enhancing AI model robustness through natural language feedback, focusing on implementation strategies and practical applications in machine learning systems.
Fine-tuning Azure OpenAI Service Models for Custom AI Applications
Master the techniques for fine-tuning Azure OpenAI models through hands-on guidance, best practices, and optimization strategies to enhance AI performance for custom applications and specific use cases.