LLMOps: Using Nvidia TensorRT SDK for GPU Inference
Optimize GPU inference using Nvidia TensorRT SDK. Convert models, compare throughput, and explore batch sizes, data precision, and runtime options for enhanced performance.
EfficientML.ai Lecture - Introduction to Efficient Machine Learning
Explore cutting-edge techniques for optimizing machine learning models, focusing on efficiency and performance in real-world applications.
Model Based Deep Learning - Applications to Imaging and Communications
Explore model-based deep learning applications in imaging and communications with expert Yonina Eldar from the Weizman Institute of Science in this ICASSP 2023 keynote presentation.
Garbage In, Garbage Out - How Purportedly Great Machine Learning Models Can Be Screwed Up by Bad Data
Explores how data quality impacts machine learning models for malicious URL detection, comparing results across different datasets and analyzing feature activations in neural networks.
Accelerating Distributed MoE Training and Inference with Lina
Explore Lina, an innovative system for accelerating distributed Mixture of Experts training and inference, addressing all-to-all communication bottlenecks in large-scale AI models.
How to Apply Deep Learning for 3D Object Recognition
Practical guide to achieving 80% accuracy in 3D object recognition using deep learning, covering data preparation, model optimization, and implementation strategies.
MLOps - Automated Machine Learning Made Easy
Explore AI and ML optimization techniques to enhance business outcomes through data understanding and model improvement.
Doubt Truth to Be a Liar - Non Triviality of Type Safety for Machine Learning
Explore type-safe feature engineering in Scala for machine learning, covering Shapeless, macros, and quasiquotes to enhance ML framework design and model accuracy.
Deep Learning with PyTorch
Comprehensive introduction to deep learning using PyTorch, covering fundamentals, computer vision applications, and practical model creation for AI enthusiasts and developers.
Streamlining Model Deployment - AI in Production
Explore strategies for optimizing AI model deployment pipelines, including open governance, runtime benchmarks, and dynamic routing. Learn to make AI deployments faster, cheaper, and more accurate in a rapidly evolving landscape.
AI Camera 개성 부여를 위한 SKT Edge AI의 차별화된 Customized AI 기술
Discover SKT의 혁신적인 Edge AI 기술로 AI 카메라의 맞춤형 학습 및 현장 최적화 방식을 통해 제한된 환경에서도 고성능 비전 AI 구현 방법을 탐구합니다.
Squash - 딥러닝 서비스 추론 속도 개선기
Discover how Squash technology optimizes deep learning inference speed and reduces hardware costs through innovative model compression techniques for efficient AI service deployment.
이미지 센서에서의 딥러닝 모델 최적화와 구현 - SK 하이닉스의 On-Sensor AI 여정
Discover how SK Hynix engineers integrate deep learning models into image sensors, exploring AI semiconductor technology for enhanced mobile device functionality and image quality optimization.
Delivering Delivery Time Prediction - Machine Learning Lessons and Model Optimization
Discover practical insights into ML model development, from handling unclear requirements to ensemble classification techniques and determining optimal probability cutoffs for delivery predictions.
Machine Learning on the Edge - From Microcontrollers to Embedded Linux Devices
Explore ML deployment on edge devices, from microcontrollers to embedded Linux systems. Learn about hardware options, model adaptation, and deployment strategies for real-world applications.
Efficient Inference of Extremely Large Transformer Models
Explore techniques for optimizing large transformer models, including compression, efficient attention, and parallelism for faster, smaller, and cost-effective inference.
Why Fixing Your Data Can Fix Your Model in Machine Learning
Explore how addressing data issues can improve machine learning models, focusing on cost-effective solutions and identifying crucial data problems to optimize resources.
End-to-end Modern Machine Learning in Production - Part 2
Explore RLHF, efficient training techniques, on-device ML, and optimizations in modern machine learning production with insights from a Hugging Face lead engineer.
Stable Diffusion on Mobile - Model Optimization for Speed and Efficiency
Optimize Stable Diffusion for mobile: Learn techniques to enhance speed and efficiency, overcoming complexity challenges for improved performance on mobile devices.
Next-Level Parameter Sharing - The Future of AI Collaboration
Explore cutting-edge multi-task learning techniques for tinyML, focusing on hard contextual parameter sharing to enhance AI collaboration and efficiency in resource-constrained environments.
4 Steps to Production LLM - Climate RAG with Weave
Improve a Climate RAG chatbot for production using Weights & Biases Weave. Learn end-to-end process including tracing, benchmarking, and incorporating feedback for iterative enhancement.