Data Driven

By Ben Frederickson

Machine Learning, Data Science and more

Data Science
A few Recommendations for a Data Scientist who wants to get started in Recommender Systems
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 …
The deepest problem with deep learning
medium.com
Some reflections on an accidental Twitterstorm, the future of AI and deep learning, and what happens when you confuse a schoolbus with a snow …
Data Science
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 …
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 …
Visualizing Matrix Factorization Using Self-Organizing Maps - Zillow AI Blog
zillow.com
Posted by ondrejl on June 12, 2018 in Machine Learning, Research One of the core methods used within Zillow’s home recommendation engine is …
The Machine Learning Reproducibility Crisis
petewarden.com - Pete Warden
Gosper Glider GunI was recently chatting to a friend whose startup’s machine learning models were so disorganized it was causing serious problems as …
Black-box optimization — Graduate Descent
timvieira.github.io - Posted by Tim Vieira
Black-box optimization algorithms are a fantastic tool that everyone should be aware of. I frequently use black-box optimization algorithms for …
The Building Blocks of Interpretability
distill.pub
Interpretability techniques are normally studied in isolation. We explore the powerful interfaces that arise when you combine them -- and the rich …
Deep Reinforcement Learning Doesn't Work Yet
alexirpan.com
June 24, 2018 note: If you want to cite an example from the post, please cite the paper which that example came from. If you want to cite the post as …
How to do machine learning efficiently
hackernoon.com
Radek OsmulskiBlockedUnblockFollowFollowing Jan 22, 2018 I have just come out of a project where 80% into it I felt I had very little. I invested a lot …
How To Create Data Products That Are Magical Using Sequence-to-Sequence Models
towardsdatascience.com
Hamel HusainBlockedUnblockFollowFollowing Jan 18, 2018 A tutorial on how to summarize text and generate features from Github Issues using deep learning …
Machine Learning
AI and Deep Learning in 2017 – A Year in Review
wildml.com - Denny Britz
The year is coming to an end. I did not write nearly as much as I had planned to. But I’m hoping to change that next year, with more tutorials around …
Implementing Poincaré Embeddings
rare-technologies.com - Jayant Jain
I have been working on implementing a model called Poincaré embeddings over the last month or so. The model is from an interesting paper by Facebook …
Optimization for Deep Learning Highlights in 2017
ruder.io - Sebastian Ruder
Table of contents:• Improving Adam• Decoupling weight decay • Fixing the exponential moving average • Tuning the learning rate • Warm restarts• SGD with …
Understanding Hinton’s Capsule Networks. Part I: Intuition.
medium.com
Max PechyonkinBlockedUnblockFollowFollowing Nov 2, 2017 Part of Understanding Hinton’s Capsule Networks Series: Part I: Intuition (you are reading it …
How to unit test machine learning code.
medium.com
Chase RobertsBlockedUnblockFollowFollowing Oct 18, 2017 Edit: The popularity of this post has inspired me to write a machine learning test library. Go …
Data Science
Word embeddings in 2017: Trends and future directions
ruder.io - Sebastian Ruder
Table of contents:• Subword-level embeddings • OOV handling • Evaluation • Multi-sense embeddings • Beyond words as points • Phrases and multi-word …
Approximate Nearest Neighbours for Recommender Systems
benfrederickson.com
One challenge that recommender systems face is in quickly generating a list of the best recommendations to show for the user. These days many …
Language identification
fasttext.cc
Fast and accurate language identification using fastText We are excited to announce that we are publishing a fast and accurate tool for text-based …
Exploring K-Means in Python, C++ and CUDA
goldsborough.me - Peter Goldsborough
Sep 10, 2017 29 minute read K-means is a popular clustering algorithm that is not only simple, but also very fast and effective, both as a quick hack …
Named Entity Recognition and the Road to Deep Learning
nlp.town
Not so very long ago, Natural Language Processing looked very different. In sequence labelling tasks such as Named Entity Recognition, Conditional …
datas-frame – Scalable Machine Learning (Part 1)
tomaugspurger.github.io - Tom Augspurger
This work is supported by Anaconda Inc. and the Data Driven Discovery Initiative from the Moore Foundation. Anaconda is interested in scaling the …
Meet Michelangelo: Uber’s Machine Learning Platform
uber.com - Jeremy Hermann & Mike Del Balso
Uber Engineering introduces Michelangelo, our machine learning-as-a-service system that enables teams to easily build, deploy, and operate ML …
DrQA
github.com - facebookresearch
README.md This is a PyTorch implementation of the DrQA system described in the ACL 2017 paper Reading Wikipedia to Answer Open-Domain Questions. Quick …
37 Reasons why your Neural Network is not working – Slav
slavv.com
Slav IvanovBlockedUnblockFollowFollowing Jul 25, 2017 The network had been training for the last 12 hours. It all looked good: the gradients were …
Deep Learning for NLP Best Practices
ruder.io - Sebastian Ruder
Update July 26, 2017: For additional context, the HackerNews discussion about this post.Table of contents:• Introduction • Best practices• Word …
Convolutional Methods for Text
medium.com
Tal PerryBlockedUnblockFollowFollowing May 21, 2017 tl;dr RNNS work great for text but convolutions can do it faster • Any part of a sentence can influence …
Revisiting the Unreasonable Effectiveness of Data
googleblog.com - Research Blog
Posted by Abhinav Gupta, Faculty Advisor, Machine Perception There has been remarkable success in the field of computer vision over the past decade, …