Deep Learning Like a Viking - Building Convolutional Neural Networks with Keras
Build a Convolutional Neural Network to recognize hand-written Viking runes using Keras, Python, and Flask. Learn CNN fundamentals and create a web application for real-time rune recognition.
Detect Anything with DarkNet/YOLO
Explore the Darknet/YOLO framework for Computer Vision, its history, and practical applications through examples. Learn how to detect objects in images and videos.
Deep Learning for Self-Driving Cars
Explore deep learning's role in autonomous driving software, addressing challenges and research in reducing traffic fatalities through AI-driven solutions.
Tips and Tricks for Intentional Text-to-Image Generation
Explore creative ML evolution in arts, observing model biases and future impacts on creative fields and popular culture through an artist's reflective perspective.
Solving Product Substitutions in Grocery E-Commerce Through Self-Supervised Machine Learning
Explore innovative self-supervised ML techniques for solving product substitution challenges in grocery e-commerce, improving customer experience and business metrics.
Artificial Intelligence and Digital Pathology: Making the Most of Limited Annotated Data
Explore semi-supervised and self-supervised approaches for efficient use of limited medical imaging datasets in AI, focusing on digital pathology applications.
Where's the Road? The Challenge of Autonomous Driving Perception in Winter
Explore challenges and advancements in autonomous driving during harsh Canadian winters, focusing on perception tasks and all-weather autonomy solutions.
Scaling Deep Learning Model Training
Learn techniques for scaling deep learning model training across distributed systems, reducing training time from days to hours while maintaining cost efficiency.
Leveraging Computer Vision and Machine Learning for Visual Inspection in Railway Systems
Explore innovative computer vision and machine learning solutions for automated visual inspection in railway systems, enhancing operational efficiency and reducing maintenance time.
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.
State-of-the-Art Deep Learning-Based Object Detection in 2D
Explore state-of-the-art object detection systems, including two-stage, one-stage, and transformer-based approaches. Learn to upgrade detection pipelines and tackle key challenges in 2D and 3D object detection.
Financial Client Churn Detection Using Computer Vision
Detect financial client churn using computer vision techniques. Convert historical client data into images and apply deep neural networks for predictive analysis.
Abstraction and Analogy in Natural and Artificial Intelligence
Explore the role of analogy-making in conceptual abstraction and understanding, and its importance for developing AI systems with humanlike intelligence.
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.
Human-Machine Collaboration Approach to Deep Learning Development
Explore human-machine collaboration in deep learning development with insights from AI expert Alexander Wong on computational imaging and computer vision.
Motion Magnification and Motion Denoising
Explore motion magnification and denoising techniques for video analysis and manipulation, including separating components and amplifying small movements in real-time applications.
Representation and Metric Learning Advances for Face and Speaker Biometric Systems
Explore advances in representation and metric learning for face and speaker biometric systems, enhancing accuracy and efficiency in identity verification.
Visual Semantics Events
Explore ambiguous image classification and multilingual video-text alignment for robust event understanding. Enhance visual models' performance on uncertain data and leverage diverse news sources.
New in Snorkel Flow 2024.R1: Enhanced Security, Image Categorization, and More
Explore Snorkel Flow's latest release: enhanced security, image categorization, LLM integrations, and document intelligence workflows for advanced AI-driven insights and custom solutions.
Large Language Models Can Help Make Better Image Classifiers
Explore how follow-up differential descriptions enhance zero-shot image classification by tailoring class descriptions, improving performance and addressing ambiguities in datasets.
Moving Beyond the First Portrait of Our Milky Way's Black Hole by Leveraging Underlying Structure
Explore computational imaging techniques used to capture black hole images and leverage data structure to extract evolving details of the Milky Way's supermassive black hole.