InfoQ Homepage Deep Learning Content on InfoQ
-
On a Deep Journey towards Five Nines
Aashish Sheshadri discusses how PayPal applies Seq2Seq networks to forecasting CPU and memory metrics at scale.
/presentations/journey-99999/en/mediumimage/Ashbig-1562248205525.JPG)
-
Document Digitization: Rethinking OCR with Machine Learning
Nischal Harohalli Padmanabha outlines the problems faced building DL networks for document process at omni:us, limitations, the evolution of team structures, engineering practices, and other topics.
/presentations/ocr-ml-doc-digitization/en/mediumimage/Nisbig-1562247900436.JPG)
-
Comparing Machine Learning Strategies Using Scikit-Learn and TensorFlow
Oliver Zeigermann looks at different ML strategies -KNN, Decision Trees, Support Vector Machines, and Neural Networks- and visualizes how they make predictions by plotting their decision boundaries.
/presentations/scikit-tensorflow/en/mediumimage/Oliver-Zeigermann-m-1561470996034.jpg)
-
Papers in Production Lightning Talks
Papers: Towards a Solution to the Red Wedding Problem, A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise, and A Machine Learning Approach to Databases Indexes.
/presentations/papers-production-lighting-talk/en/mediumimage/papers-production-lighting-talk-m-1559576642650.jpg)
-
Debuggable Deep Learning
Mantas Matelis and Avesh Singh explain how they debugged DeepHeart, a DNN that detects cardiovascular disease from heart rate data.
/presentations/debug-dl/en/mediumimage/debug-dl-m-1560930105231.jpg)
-
Scaling Deep Learning to Petaflops and beyond!
Prabhat explores 2D and 3D convolutional architectures for solving pattern classification, regression and segmentation problems in high-energy physics, cosmology and climate science.
/presentations/scale-dl-petaflops/en/mediumimage/Prabig-1560900970972.JPG)
-
Ludwig: A Code-Free Deep Learning Toolbox
Piero Molino introduces Ludwig, a deep learning toolbox that allows to train models and to use them for prediction without the need to write code.
/presentations/ludwig-dl-toolbox/en/mediumimage/piero_molino-h-1559952531778.jpeg)
-
Deep Learning on Microcontrollers
Pete Warden discusses why Deep Learning is a great fit for tiny, cheap devices, what can be built with it, and how to get started.
/presentations/dl-microcontrollers/en/mediumimage/Pete-Warden-m-1559787428228.jpeg)
-
Understanding Deep Learning
Jessica Yung talks about the foundational concepts about neural networks and highlights key things to pay attention to: learning rates, how to initialize a network, and more.
/presentations/understanding-deep-learning/en/mediumimage/Jessica-Yung-m-1558000059616.jpg)
-
Jupyter Notebooks: Interactive Visualization Approaches
Chakri Cherukuri talks about how to understand and visualize machine learning models using interactive widgets and introduces the widget libraries.
/presentations/ml-models-jupyter/en/mediumimage/Chakri-Cherukuri-m-1554358378987.jpg)
-
Machines Can Learn - a Practical Take on Machine Intelligence Using Spring Cloud Data Flow and TensorFlow
Christian Tzolov showcases how building a complex use-case, such as real-time image recognition or object detection, can be simplified with the help of the Spring Ecosystem and TensorFlow.
/presentations/ml-spring-tensorflow/en/mediumimage/Christian-Tzolov-m-1547811672531.jpeg)
-
AI for Software Testing with Deep Learning: Is It Possible?
Emerson Bertolo discusses lessons learned when using pre-trained Convolutional Neural Networks (CNN) models, Image Detection APIs and CNN's built from scratch for this purpose.
/presentations/software-testing-deep-learning/en/mediumimage/emerson-bertolo-m-1544625558541.jpg)