InfoQ Homepage Machine Learning Content on InfoQ
-
Deep Learning for Application Performance Optimization
Zoran Sevarac presents his experience and best practice for autonomous, continuous application performance tuning using deep learning.
/presentations/dl-performance-optimization/en/mediumimage/Zorbig-1534991422721.JPG)
-
Neural Networks across Space and Time
Dave Snowdon starts with a brief introduction to deep neural networks, why they are important and how they work. He covers 2 of the most important deep neural architectures: convolutional & recurrent.
/presentations/neural-networks-convolutional-recurrent/en/mediumimage/Davebig-1530407960524.JPG)
-
Simplifying ML Workflows with Apache Beam
Tyler Akidau discusses how Apache Beam is simplifying pre- and post-processing for ML pipelines.
/presentations/ml-workflow-apache-beam/en/mediumimage/Tybig-1529542935186.JPG)
-
Understanding Software System Behavior with ML and Time Series Data
David Andrzejewski discusses how time series datasets can be combined with ML techniques in order to aid in the understanding of system behaviors in order to improve performance and uptime.
/presentations/ml-time-series/en/mediumimage/Understanding-Software-System-Behavior-with-ML-and-time-series-data-ribbon-1530265468916.jpg)
-
Analyzing & Preventing Unconscious Bias in Machine Learning
Rachel Thomas keynotes on three case studies, attempting to diagnose bias, identify some sources, and discusses what it takes to avoid it.
/presentations/unconscious-bias-machine-learning/en/mediumimage/Analyzing-Preventing-Unconscious-bias-in-Machine-Learning-ribbon-1530264897468.jpg)
-
Models in Minutes not Months: AI as Microservices
Sarah Aerni talks about how Salesforce built an AI platform that scales to thousands of customers.
/presentations/salesforce-ai-microservices/en/mediumimage/Sabig-1528505806733.JPG)
-
Understanding ML/DL Models using Interactive Visualization Techniques
Chakri Cherukuri discusses how to use visualization techniques to better understand machine learning and deep learning models.
/presentations/ml-dl-visualization/en/mediumimage/Chabig-1528337189646.JPG)
-
Interpretable Machine Learning Products
Mike Lee Williams discusses how interpretability can make deep neural networks models easier to understand, and describes LIME, an OS tool that can be used to explore what ML classifiers are doing.
/presentations/ml-interpretability-lime/en/mediumimage/Mikebig-1528336770231.JPG)
-
Machine Intelligence at Google Scale
Guillaume LaForge presents pre-trained ML services such as Cloud Vision API and Speech API that works without any training, introducing Cloud AutoML.
/presentations/google-ml-services/en/mediumimage/Gubig-1527955175142.JPG)
-
Real-Time Data Analysis and ML for Fraud Prevention
Mikhail Kourjanski addresses the architectural approach towards the PayPal internally built real-time service platform, which delivers performance and quality of decisions.
/presentations/paypal-data-analysis-ml-fraud/en/mediumimage/Mikbig-1527943584688.JPG)
-
End-to-End ML without a Data Scientist
Holden Karau discusses how to train models, and how to serve them, including basic validation techniques, A/B tests, and the importance of keeping models up-to-date.
/presentations/ml-models-ab-tests/en/mediumimage/End-to-End-ML-without-Data-Scientist-ribbon-1530266022644.jpg)
-
Deep Learning for Science
Prabhat discusses machine learning's impact on climatology, astronomy, cosmology, neuroscience, genomics, and high-energy physics, and the future of AI in powering scientific discoveries.
/presentations/deep-learning-science/en/mediumimage/Prabig-1527731821296.JPG)