Novelty in Machine Learning, or “What Gets Me Excited Every Day About Data Science”
Note: Kirk will present two training sessions at ODSC East 2020. One will focus on “Solving the Data Scientist’s Dilemma: the Cold-Start Problem with 10+ Machine Learning Examples” and the other will look at “Adapting Machine Learning Algorithms to Novel Use Cases.” I have always appreciated the unusual, unexpected,... Read more
Variational Auto-Encoders for Customer Insight
Github repository: VAEs-in-Economics Neural networks are sometimes perceived as super complicated. They’re not. The most attractive application, in my opinion, of neural networks for small and medium-sized businesses, is in customer segmentation, and in my upcoming workshop at ODSC East 2020, “Variational Auto-Encoders for Customer Insight,” I will show... Read more
Tutorial: Accelerate and Productionize ML Model Inferencing Using Open-Source Tools
Faith and Prabhat are speakers for ODSC East 2020 this April. Be sure to check out their talk, “From Research to Production: Performant Cross-platform ML/DNN Model Inferencing on Cloud and Edge with ONNX Runtime,” there! You’ve finally got that perfect trained model for your data set. Now what? To... Read more
Causal Analysis Provides a Toolbelt, Not a Silver Bullet
Erich is a speaker for ODSC East 2020 this April 13-17! Be sure to check out his talk, “Methods for Using Observational Data to Answer Causal Questions,” there! Is drinking red wine associated with decreased risk of heart disease? Does drinking red wine prevent heart disease? Should I advise... Read more
Data Science Applied to Wearables: Can Your Watch Help You Improve Your Lifestyle?
Svetlana is a speaker for ODSC East 2020 this April 13-17! Be sure to check out her talk, “Biomarker, Sleep, and Activity Patterns Data from a Web-Based Nutrition Platform for Healthy Individuals: Insights for Personalized Recommendations,” there! Activity trackers have made the inner workings of our bodies accessible to... Read more
Guided Labeling: Human-in-the-Loop Label Generation with Active Learning and Weak Supervision
Paolo is a speaker for ODSC East 2020 this April 13-17. Be sure to check out his talk, “Guided Labeling: Human-in-the-Loop Label Generation with Active Learning and Weak Supervision,” there! One of the key challenges of utilizing supervised machine learning for real-world use cases is that most algorithms and... Read more
A Survey of Popular Ensembling Techniques – Part 1
Statisticians have long known that two heads are better than one, but three is even better. Sir Francis Galton, the polymathic giant behind the pairwise correlation, regression, et al., writes about the surprising power of Vox Populi—“voice of the people” if you’re Roman—to make predictions about unknown quantities superior... Read more
Mixing Topology and Deep Learning with PersLay
In a former post, I presented Topological Data Analysis and its main descriptor, the so-called persistence diagram. In this post, I would like to show how these descriptors can be combined with neural networks, opening the way to applications based upon both deep learning and topology! What are persistence diagrams? Briefly, a persistence... Read more
10 Notable Frameworks for NLP
Natural Language Processing hit its big stride back in 2017 with the introduction of Transformer Architecture from Google. State of the art approaches helped bridge the gap between humans and machines and helped us build bots capable of using human language undetected. It’s an exciting time. You’re going to... Read more
State-of-the-art NLP Made Easy with AdaptNLP
Andrew and Brian are speakers for ODSC East 2020 this April 13-17 in Boston. Be sure to check out their talk, “State-of-the-art NLP Made Easy,” there! Natural Language Processing (NLP) has advanced significantly since 2018, when ULMFiT and Google’s release of the BERT language model approached human-level performance on... Read more