InfoQ Homepage Machine Learning Content on InfoQ
-
Comparing Deep Learning Frameworks
Jeffrey Shomaker covers the different types of deep learning frameworks and then focuses on neural networks, including business uses and 4 of the main systems (eg. Tensor Flow) that are open sourced.
/presentations/comparison-deep-learning-frameworks/en/mediumimage/Jefbig.JPG)
-
Deep Learning Applications in Business
Diego Klabjan discusses models, implementations, and challenges developing applications for trading, forecasting, and healthcare, detailing relevant models and issues adopting and deploying them.
/presentations/deep-learning-business/en/mediumimage/Diebig.JPG)
-
Machine Learning at Scale
Aditya Kalro discusses using large-scale data for Machine Learning (ML) research and some of the tools Facebook uses to manage the entire process of training, testing, and deploying ML models.
/presentations/machine-learning-scale/en/mediumimage/Adbig.JPG)
-
Products and Prototypes with Keras
Micha Gorelick shows how to build a working product with Keras, a high-level deep learning framework, discussing design decisions, and demonstrating how to train and deploy a model.
/presentations/keras/en/mediumimage/Micabig.JPG)
-
Deep Learning at Scale
Scott Le Grand describes his work at NVidia, Amazon and Teza, including the DSSTNE distributed deep learning framework.
/presentations/dsstne-deep-learning/en/mediumimage/Scobig.JPG)
-
Building Robust Machine Learning Systems
Stephen Whitworth talks about his experience at Ravelin, and provides useful practices and tips to help ensure our machine learning systems are robust, well audited, avoid embarrassing predictions.
/presentations/ravelin-ml-best-practices/en/mediumimage/STebig.JPG)
-
Using NLP, Machine Learning & Deep Learning Algorithms to Extract Meaning from Text
David Talby walks through building a natural language annotations pipeline with domain-specific annotators, and using deep learning to automatically expand and update taxonomies.
/presentations/nlp-machine-learning-meaning-text/en/mediumimage/Davbig.JPG)
-
Policing the Stock Market with Machine Learning
Cliff Click talks about SCORE, a solution for doing Trade Surveillance using H2O, Machine Learning, and a whole lot of domain expertise and data munging.
/presentations/score-ml-stock-market/en/mediumimage/Cliffbig.JPG)
-
Predictability in ML Applications
Claudia Perlich presents scenarios in which the combination of different and highly informative features can have significantly negative overall impact on the usefulness of predictive modeling.
/presentations/ml-predictability/en/mediumimage/Clabig.JPG)
-
Using Bayesian Optimization to Tune Machine Learning Models
Scott Clark introduces Bayesian Global Optimization as an efficient way to optimize ML model parameters, explaining the underlying techniques and comparing it to other standard methods.
/presentations/bayesian-optimization-ml/en/mediumimage/Scobig.JPG)
-
Machine Learning Your Way to Smarter API Error Responses
Steven Cooper discusses using machine learning to understand malformed API requests to not only respond with a best fit response, but capture the user errors for future responses.
/presentations/machine-learning-api-response/en/mediumimage/Stebig.JPG)
-
Autonomous Operations: Microservices, ML and AI
Rob Harrop discusses the increasing automated field of operations and what the future might hold when machine learning and AI techniques are brought to bear on the problem of systems operations.
/presentations/microservices-ml-ai/en/mediumimage/Robbig.JPG)