Feature Selection for Machine Learning
Explore feature selection methods for machine learning, including filter, wrapper, and embedded approaches. Learn to choose the most predictive variables for production-ready models.
The Fairness of Fairness: Evaluating, Monitoring, and Impacts of ML in Insurance
Explore strategies for creating fair ML models in insurance, covering bias metrics, optimization techniques, and insights from FTC research on credit-based insurance scores' impact.
Building Qrio, a Bot That Plays Videos for My Toddler
Discover how to build an AI bot that interacts with toddlers, recognizes toys, and plays relevant YouTube Kids videos. Learn about object detection, text-to-speech, animation, and automation techniques.
vLLM - Servidor Especializado en Inferencia de LLMs
Descubre cómo implementar y optimizar servidores de inferencia LLM con vLLM, una tecnología especializada para el procesamiento eficiente de modelos de lenguaje a gran escala.
Deploying GenAI on Edge Devices with ExecuTorch - Technical Overview
Discover how to deploy machine learning models on edge devices using ExecuTorch, featuring insights on memory optimization, hardware compatibility, and efficient model conversion techniques.
Navigating LLM Deployment - Tips, Tricks and Techniques
Master essential strategies for optimizing and deploying self-hosted language models, covering best practices for monitoring, implementation, and maximizing value across industries like finance and healthcare.
Hyperparameter Tuning on the Cloud - Optimizing Machine Learning Models with SEER and Rubberband
Master hyperparameter tuning optimization in cloud environments through SEER algorithm and Rubberband system, focusing on maximizing model accuracy while minimizing costs and time constraints.
Engineers Guide for Shepherding Models into Production
Discover essential engineering practices for deploying machine learning models into production systems, from input/output definition to optimization and integration within larger infrastructures.
Deploying Transformers at Scale - Addressing Challenges and Increasing Performance
Explore challenges and solutions for deploying large-scale Transformer networks, focusing on improving latency, throughput, and cost-effectiveness for processing massive datasets.
Cost Reduction Methods for Machine Learning in Production
Discover effective strategies to reduce costs when deploying machine learning models in production, focusing on optimizing models and infrastructure for cost-efficient MLOps.
Hyperparameter Tuning with a Focus on Weights and Biases Sweeps
Explore hyperparameter tuning strategies and visualizations for deep learning models, focusing on Weights & Biases Sweeps. Accelerate progress in semantic segmentation and language understanding projects.
Unlocking Mixture of Experts - From One Know-it-all to a Group of Jedi Masters
Explore Mixture of Experts technique to enhance predictive powers. Dive into principles, challenges, and applications. Learn when to use MoE, discuss business metrics, and access resources for implementation.
Fine-Tuning LLMs: Best Practices and When to Go Small - Lecture 124
Explore best practices for fine-tuning LLMs, including strategies for improving performance, overcoming challenges, and determining when to use smaller models for specific tasks.
Real-Time Audio Source Separation on iOS Devices
Explore real-time audio source separation on iOS, covering deep learning algorithms, model optimization, and low-latency integration for innovative music interaction and learning applications.
Deep Dive - Unpacking the TinyML Cookbook
Explore practical TinyML applications and techniques with expert Gian Marco Iodice, gaining insights into efficient machine learning on resource-constrained devices.
Building Chatbots with Hugging Face LLMs - 5 Expert Tips
Discover 5 expert engineering tips for building chatbots using open-source LLMs like Mistral. Learn crucial technical nuances for transitioning from proprietary APIs to open-source models.
Sparse Training of Neural Networks Using AC/DC
Explore AC/DC, a novel sparse training algorithm for DNNs. Learn its benefits, implementation, and deployment for improved performance and accuracy in deep learning.
Unlock Faster and More Efficient LLMs with SparseGPT - Neural Magic
Optimize LLMs with SparseGPT: prune and quantize models for efficient CPU deployment at GPU speeds. Explore one-shot compression, benchmarks, and practical implementation.
How to Pick a GPU and Inference Engine for Large Language Models
Explore GPU selection and inference engine optimization for large language models. Compare quantization effects, software options, and cost-efficiency across various GPUs and model sizes.
EfficientML.ai Lecture - Introduction to Efficient Machine Learning
Explore cutting-edge techniques for optimizing machine learning models, focusing on efficiency and performance in AI applications.
LLM Post-Training Techniques - Lecture 14
Dive into advanced LLM post-training techniques and deployment strategies, exploring optimization methods and practical implementation approaches for efficient language model deployment.