Understanding hidden memories of recurrent neural networks

February 25, 2019May 25, 2020 ~ Adrian Colyer ~ Leave a comment

Understanding hidden memories of recurrent neural networks Ming et al., VAST’17 Last week we looked at CORALS, winner of round 9 of the Yelp dataset challenge. Today’s paper choice was a winner in round 10. We’re used to visualisations of CNNs, which give interpretations of what is being learned in the hidden layers. But the ... Continue Reading

CORALS: who are my potential new customers? Tapping into the wisdom of customers’ decisions

February 22, 2019May 25, 2020 ~ Adrian Colyer ~ 3 Comments

CORALS: who are my potential new customers? Tapping into the wisdom of customers' decisions Li et al., WSDM'19 The authors of this paper won round 9 of the Yelp dataset challenge for their work. The goal is to find new target customers for local businesses by mining location-based checkins of users, user preferences, and online ... Continue Reading

Protecting user privacy: an approach for untraceable web browsing history and unambiguous user profiles

February 20, 2019May 25, 2020 ~ Adrian Colyer ~ 2 Comments

Protecting user privacy: an approach for untraceable web browsing history and unambiguous user profiles Beigi et al., WSDM'19 Maybe you’re reading this post online at The Morning Paper, and you came here by clicking a link in your Twitter feed because you follow my paper write-up announcements there. It might even be that you fairly ... Continue Reading

The why and how of nonnegative matrix factorization

February 18, 2019May 25, 2020 ~ Adrian Colyer ~ 14 Comments

The why and how of nonnegative matrix factorization Gillis, arXiv 2014 from: ‘Regularization, Optimization, Kernels, and Support Vector Machines.’ Last week we looked at the paper ‘Beyond news content,’ which made heavy use of nonnegative matrix factorisation. Today we’ll be looking at that technique in a little more detail. As the name suggests, ‘The Why ... Continue Reading

A survey on dynamic and stochastic vehicle routing problems

February 15, 2019May 25, 2020 ~ Adrian Colyer ~ 3 Comments

A survey on dynamic and stochastic vehicle routing problems Ritzinger et al., International Journal of Production Research It’s been a while since we last looked at an overview of dynamic vehicle routing problems: that was back in 2014 (See ‘Dynamic vehicle routing, pickup, and delivery problems’). That paper has fond memories for me, I looked ... Continue Reading

ExFaKT: a framework for explaining facts over knowledge graphs and text

February 11, 2019May 25, 2020 ~ Adrian Colyer ~ 6 Comments

ExFaKT: a framework for explaining facts over knowledge graphs and text Gad-Elrab et al., WSDM'19 Last week we took a look at Graph Neural Networks for learning with structured representations. Another kind of graph of interest for learning and inference is the knowledge graph. Knowledge Graphs (KGs) are large collections of factual triples of the ... Continue Reading

Graph neural networks: a review of methods and applications

February 8, 2019May 25, 2020 ~ Adrian Colyer ~ Leave a comment

Graph neural networks: a review of methods and applications Zhou et al., arXiv 2019 It’s another graph neural networks survey paper today! Cue the obligatory bus joke. Clearly, this covers much of the same territory as we looked at earlier in the week, but when we’re lucky enough to get two surveys published in short ... Continue Reading

A comprehensive survey on graph neural networks

February 6, 2019May 25, 2020 ~ Adrian Colyer ~ 6 Comments

A comprehensive survey on graph neural networks Wu et al., arXiv'19 Last year we looked at ‘Relational inductive biases, deep learning, and graph networks,’ where the authors made the case for deep learning with structured representations, which are naturally represented as graphs. Today’s paper choice provides us with a broad sweep of the graph neural ... Continue Reading

TensorFlow.js: machine learning for the web and beyond

February 4, 2019May 25, 2020 ~ Adrian Colyer ~ 6 Comments

TensorFlow.js: machine learning for the web and beyond Smilkov et al., SysML'19 If machine learning and ML models are to pervade all of our applications and systems, then they’d better go to where the applications are rather than the other way round. Increasingly, that means JavaScript - both in the browser and on the server. ... Continue Reading

the morning paper

a random walk through Computer Science research, by Adrian Colyer
Made delightfully fast by strattic

Uncategorized