Object Detection on Custom Dataset with YOLO - Fine-Tuning with PyTorch and Python Tutorial
Fine-tune YOLO v5 for custom object detection using PyTorch. Learn model installation, training, evaluation, and application on a clothing dataset.
How to Train Object Detection Transformer on Custom Dataset
Learn to train Object Detection Transformers using DETR, from environment setup to custom dataset training and model evaluation. Covers PyTorch, COCO datasets, and PyTorch Lightning for efficient deep learning workflows.
Beyond Testset Performance - Strategies for Clinical Deployment
Strategies for deploying AI in clinical settings, addressing challenges beyond test performance. Explores model reliability, distribution shifts, and human-AI collaboration for real-world medical applications.
Mandoline - Model Evaluation under Distribution Shift
Explores a novel framework for evaluating machine learning models under distribution shifts, using slice-based reweighting to improve performance estimation on target distributions.
Stanford Seminar - Human-AI Interaction Under Societal Disagreement
Explores Jury Learning, an interactive AI architecture enabling developers to consider diverse perspectives in machine learning, addressing societal disagreements in AI decision-making processes.
How Can You Trust Machine Learning?
Explore a framework for trustworthy AI based on Clarity, Competence, and Alignment. Learn about explainable ML, rigorous model evaluation, and aligning AI behaviors with human values.
Evaluation of Generative Models - Stanford CS236 Deep Generative Models Lecture 15
Explore evaluation methods for deep generative models, including metrics and techniques to assess model performance, quality, and effectiveness in various applications.
Introduction to Machine Learning for Coders
Learn essential machine learning concepts and techniques for coders, covering fundamental principles and practical applications across 12 comprehensive lessons.
Natural Language Processing
Accelerated introduction to NLP, covering machine learning basics, text preprocessing, vectorization, and advanced neural network architectures like RNNs, LSTMs, and Transformers.
Computer Vision
Explore machine learning and computer vision fundamentals, advanced neural network architectures, and applications in object detection and semantic segmentation.
Tabular Data
Learn machine learning techniques for tabular data, including model evaluation, feature engineering, tree-based models, hyperparameter tuning, and neural networks using AWS SageMaker.
Optimizing CI/CD Model Management and Evaluation Workflows with Weights & Biases
Learn to enhance CI/CD pipelines for efficient deployment of top production models using Weights & Biases. Explore key concepts and benefits of effective CI/CD pipelines, implement W&B Registry as a central repository for models and datasets, and constru…
GenAI in Production with MLflow
Explore recent advancements in GenAI application lifecycle management with MLflow in this 20-minute talk by Ben Wilson, Tech Lead of the AI OSS Ecosystem team at Databricks. Discover supported integrations for GenAI application tracking, evaluation, depl…
Evaluating Open-Source Local LLMs: A Comparative Analysis with Proprietary Giants for Developer Applications
Explore the world of open-source local large language models (LLMs) in this 40-minute conference talk from Devoxx. Dive into a comparative analysis between these models and proprietary giants, focusing on their performance, flexibility, and applicability…
Pushing LLMs over the Edge: Exploring the Limits of the Possible
Explore LLM limits through outrageous applications using LangChain4j and Quarkus. Witness complex tasks, potential havoc, and self-evaluating models in this thrilling journey of AI possibilities.
Is Your Machine Learning Model Trustworthy? Evaluating AI Quality and Reliability
Explore AI quality pillars, their importance, and evaluation methods to ensure trustworthy ML models. Learn automated techniques for assessing model performance, robustness, and explainability.
Applying Responsible AI with the Open-Source LangTest Library
Explore open-source tools for building safe, fair AI models. Learn to address robustness, bias, and data leakage challenges using the LangTest library in MLOps workflows.
Towards Robust GenAI: Techniques for Evaluating Enterprise LLM Applications
Discover emerging automated evaluation solutions for LLMs, combining micro evaluators and human feedback to confidently deploy AI in enterprise applications.
Automated Monitoring in Production for Continuous Model Improvements
Implement automated monitoring for ML models in production. Continuously evaluate performance, visualize metrics, detect degradation, and correlate issues with input data for quick debugging and improvement.
CyclOps: A Framework for Data Extraction, Model Evaluation and Drift Detection in Clinical Machine Learning
Explore CyclOps, a unified framework for healthcare ML, enabling data extraction, model evaluation, and drift detection in clinical settings. Streamline development of robust AI models.
OpenAI Fine-tuning vs Distillation - Techniques and Implementation
Explore OpenAI fine-tuning and distillation techniques using a free Colab notebook. Learn to generate datasets, run fine-tuning, and evaluate models for improved AI performance.