Ben Frederickson AI Research, Replicability and Incentives dennybritz.com More people than ever are working on Deep Learning. Journal and arXiv submissions have increased by ~5x over the past few years. If you consider …
Ben FredericksonBuilding Recommender SystemsBy Arnie B.Here is a curated collection of my favourite posts for people starting out in recommender systems and personalization. This was created in preparation for our summer interns in the recommendations team at Flipboard!
Ben Frederickson A Case For Embeddings In Recommendation Problems abhadury.com Once you have worked on different machine learning problems, most things in the field start to feel very similar. You take your raw input data, map …
Ben FredericksonArtificial Intelligence An Epidemic of AI Misinformation thegradient.pub - Gary Marcus Maybe every paper abstract should have a mandatory field of what the limitations of the proposed approach are. That way some of the science …
Ben FredericksonTensorFlow The State of Machine Learning Frameworks in 2019 thegradient.pub - Horace He Since deep learning regained prominence in 2012, many machine learning frameworks have clamored to become the new favorite among researchers and …
Ben Frederickson Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches arxiv.org - Maurizio Ferrari Dacrema, Paolo Cremonesi, Dietmar Jannach Computer Science > Information Retrieval Abstract: Deep learning techniques have become the method of choice for researchers working on algorithmic …
Ben Frederickson Simulating A/B tests offline with counterfactual inference abhadury.com While developing machine learning (ML) algorithms in production environments, we usually optimize a function or a loss that has nothing to do with …
Ben Frederickson A few Recommendations for a Data Scientist who wants to get started in Recommender Systems - BBVA AI Factory bbvadata.com As a Data Scientist, you are expected to be able to build all sort of data products, that may involve simple-yet highly valuable business trends …
Ben Frederickson The deepest problem with deep learning Medium - Gary Marcus On November 21, I read an interview with Yoshua Bengio in Technology Review that to a suprising degree downplayed recent successes in deep learning, …
Ben FredericksonMachine Learning NLP's ImageNet moment has arrived thegradient.pub - Sebastian Ruder Big changes are underway in the world of Natural Language Processing (NLP).The long reign of word vectors as NLP’s core representation technique has …
Ben FredericksonMachine Learning AdamW and Super-convergence is now the fastest way to train neural nets fast.ai Written: 02 Jul 2018 by Sylvain Gugger and Jeremy Howard Note from Jeremy: Welcome to fast.ai’s first scholar-in-residence, Sylvain Gugger. What better …
