Self-driving database management systems Pavlo et al., CIDR 2017 We've previously seen many papers looking into how distributed and database systems technologies can support machine learning workloads. Today's paper choice explores what happens when you do it the other way round - i.e., embed machine learning into a DBMS in order to continuously optimise its … Continue reading Self-driving database management systems
Tag: Machine Learning
Learning to learn by gradient descent by gradient descent
Learning to learn by gradient descent by gradient descent Andrychowicz et al. NIPS 2016 One of the things that strikes me when I read these NIPS papers is just how short some of them are - between the introduction and the evaluation sections you might find only one or two pages! A general form is … Continue reading Learning to learn by gradient descent by gradient descent
TensorFlow: A system for large-scale machine learning
TensorFlow: A system for large-scale machine learning Abadi et al. (Google Brain) OSDI 2016 This is my last paper review for 2016! The Morning Paper will be taking a two week break for the holidays, resuming again on the 2nd January. Sometime inbetween I’ll do a short retrospective on the year. It seems fitting to … Continue reading TensorFlow: A system for large-scale machine learning
Building machines that learn and think like people
Building machines that learn and think like people Lake et al., arXiv 2016 Pro-tip: if you're going to try and read and write up a paper every weekday, it's best not to pick papers that run to over 50 pages. When the paper is as interesting as "Building machines that learn and think like people" … Continue reading Building machines that learn and think like people
Smart Reply: Automated response suggestion for email
Smart Reply: Automated response suggestion for email Kannan, Kaufman, Karach, et al. KDD 2016 I’m sure you’ve come across (or at least heard of) Google Inbox’s smart reply feature for mobile email by now. It’s currently used for 10% of all mobile replies, which must equate to a very large number of messages per day. … Continue reading Smart Reply: Automated response suggestion for email
Incremental knowledge base construction using DeepDive
Incremental knowledge base construction using DeepDive Shin et al., VLDB 2015 When I think about the most important CS foundations for the computer systems we build today and will build over the next decade, I think about Distributed systems Database systems / data stores (dealing with data at rest) Stream processing (dealing with data in … Continue reading Incremental knowledge base construction using DeepDive
Cyclades: Conflict-free asynchronous machine learning
CYCLADES: Conflict-free asynchronous machine learning Pan et al. NIPS 2016 "Conflict-free," the magic words that mean we can process things concurrently or in parallel at full speed, with no need for coordination. Today's paper introduces Cyclades, a system for speeding up machine learning on a single NUMA node. In the evaluation, the authors used NUMA … Continue reading Cyclades: Conflict-free asynchronous machine learning
Why should I trust you? Explaining the predictions of any classifier
“Why Should I Trust You? Explaining the Predictions of Any Classifier Ribeiro et al., KDD 2016 You’ve trained a classifier and it’s performing well on the validation set - but does the model exhibit sound judgement or is it making decisions based on spurious criteria? Can we trust the model in the real world? And … Continue reading Why should I trust you? Explaining the predictions of any classifier
Ten challenges in highly-interactive dialog systems
Ten challenges in highly-interactive dialog systems Ward &De Vault AAAI 2015 It’s time to end our look into the technology behind chatbots and dialog systems - there’s a huge crop of SIGMOD 2016 papers waiting to be explored for starters! To end the mini-series, today I’ve chosen a 2015 position paper from Ward and De … Continue reading Ten challenges in highly-interactive dialog systems
Multi-domain dialog state tracking using recurrent neural networks
Multi-domain dialog state tracking using recurrent neural networks a Mrksic et al. 2015 Suppose you want to build a chatbot for a domain in which you don’t have much data yet. What can you do to bootstrap your dialog state tracking system? In today’s paper the authors show how to transfer knowledge across domains, and … Continue reading Multi-domain dialog state tracking using recurrent neural networks
the morning paper 