InfoQ Homepage Machine Learning Content on InfoQ
-
Getting Started in Deep Learning with TensorFlow 2.0
Brad Miro explains what deep learning is, why one may want to use it over traditional ML methods, as well as how to get started building deep learning models using TensorFlow 2.0.
/presentations/dl-tensorflow-2/en/mediumimage/Bradbig-1566227272234.JPG)
-
Hands-on Feature Engineering for Natural Language Processing
Susan Li shares various NLP feature engineering techniques, from Bag-Of-Words to TF-IDF to word embedding that includes feature engineering for both ML models and an emerging deep learning approach.
/presentations/nlp-ml-dl/en/mediumimage/Susan-Li-m-1565253940360.jpg)
-
Deep Learning for Recommender Systems
Oliver Gindele discusses how some DL models can be implemented in TensorFlow, starting from a collaborative filtering approach and extending that to more complex deep recommender systems.
/presentations/dl-models-tensorflow/en/mediumimage/Oliver-Gindele-m-1564599110695.jpg)
-
Panel: First Steps with Machine Learning
The panelists discuss the first principles to follow when adding ML to a system.
/presentations/ml-first-steps/en/mediumimage/ml-first-steps-m-1563461180264.jpg)
-
Deep Learning with Audio Signals: Prepare, Process, Design, Expect
Keunwoo Choi introduces what the audio/music research societies have discovered while playing with deep learning when it comes to audio classification and regression.
/presentations/dl-audio-signal/en/mediumimage/Keubig-1562978446035.JPG)
-
DeepRacer and DeepLens, Machine Learning for Fun! (and Profit?)
Jeremy Edberg shares his work with DeepRacer and DeepLens, talking about some of the basics of ML used in these projects and showing a DeepRacer in action.
/presentations/deepracer/en/mediumimage/Jerbig-1562978039209.JPG)
-
Reinforcement Learning: A Gentle Introduction with a Real Application
Christian Hidber shows “how” and “why” Reinforcement Learning works, using as a practical example siphonic roof drainage.
/presentations/reinforcement-learning/en/mediumimage/Christian-Hidber-m-1562246330694.jpg)
-
Policing the Capital Markets with ML
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/capital-markets-ml/en/mediumimage/Cliff-Click-m-1559583454114.jpg)
-
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)
-
Code Your Way out of a Paper Bag
Frances Buontempo discusses how to program your way out of the paper bag using machine learning techniques.
/presentations/program-out-paper-bag-ml/en/mediumimage/Frances-Buontempo-m-1559892811035.jpg)