Memory Networks

March 10, 2016 ~ Adrian Colyer ~ 14 Comments

Memory Networks Weston et al. 2015 As with the Neural Turing Machine that we look at yesterday, this paper looks at extending machine learning models with a memory component. The Neural Turing Machine work was developed at Google by the DeepMind team, today's paper on Memory Networks was developed by the Facebook AI Research group. ... Continue Reading

Neural Turing Machines

March 9, 2016 ~ Adrian Colyer ~ 15 Comments

Neural Turing Machines - Graves et al. 2014 (Google DeepMind) A Neural Turing Machine is a Neural Network extended with a working memory, which as we'll see, gives it very impressive learning abilities. A Neural Turing Machine (NTM) architecture contains two basic components: a neural network controller and a memory bank. Like most neural networks, ... Continue Reading

CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy

March 8, 2016 ~ Adrian Colyer ~ 8 Comments

CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy - Downlin et al. 2016 Fixed misspellings of homomorphic ! With the rise of machine learning, it's easy to imagine all sorts of cloud services that can process your data and make predictions of some kind (Machine Learning as a Service - MLAS). ... Continue Reading

Trajectory Data Mining: An Overview

March 7, 2016 ~ Adrian Colyer ~ 2 Comments

Trajectory Data Mining: An Overview - Zheng 2015 In 'Trajectory Data Mining,' Zheng conducts a high-level tour of the techniques involved in working with trajectory data. This is the data created by a moving object, as a sequence of locations, often with uncertainty around the exact location at each point. This could be GPS trajectories ... Continue Reading

Google’s Hybrid Approach to Research

March 4, 2016 ~ Adrian Colyer ~ Leave a comment

Google's Hybrid Approach to Research - Spector et al. 2012 Something a little different to close out the week, a paper describing how Google conduct research. It's a fascinating look at how they balance fundamental and applied research, how they integrate research into product teams, and how they measure the contribution of the research. I ... Continue Reading

Inferring Causal Impact Using Bayesian Structural Time-Series Models

March 3, 2016 ~ Adrian Colyer ~ 4 Comments

Inferring Causal Impact Using Bayesian Structural Time-Series Models - Brodersen et al. (Google) 2015 Today's paper comes from 'The Annals of Applied Statistics' - not one of my usual sources (!), and a good indication that I'm likely to be well out of my depth again for parts of it. Nevertheless, it addresses a really ... Continue Reading

Graying the Black Box: Understanding DQNs

March 2, 2016 ~ Adrian Colyer ~ 13 Comments

Graying the Black Box: Understanding DQNs - Zahavy et al. 2016 It's hard to escape the excitement around deep learning these days. Over the last couple of days we looked at some of the lessons learned by Google's machine learning systems teams, including the need to develop ways of getting insights into the predictions made ... Continue Reading

Ad Click Prediction: A View from the Trenches

March 1, 2016 ~ Adrian Colyer ~ 2 Comments

Ad Click Prediction: a View from the Trenches - McMahan et al. 2013 Yesterday we looked at a tour through the many ways technical debt can creep into machine learning systems. In that paper, the authors mention an automated feature management tool that since its adoption, "has regularly allowed a team at Google to safely ... Continue Reading

Machine Learning: The High-Interest Credit Card of Technical Debt

February 29, 2016 ~ Adrian Colyer ~ 9 Comments

Machine Learning: The High-Interest Credit Card of Technical Debt - Sculley et al. 2014 Today's paper offers some pragmatic advice for the developers and maintainers of machine learning systems in production. It's easy to rush out version 1.0 the authors warn us, but making subsequent improvements can be unexpectedly difficult. You very much get the ... Continue Reading

Distributed Consistency and Session Anomalies

February 26, 2016 ~ Adrian Colyer ~ 13 Comments

Since we've spent the last couple of days sketching anomaly diagrams and looking at isolation levels, I wanted to finish the week off with a quick recap of session anomalies and consistency levels for distributed stores. In terms of papers, I've drawn primary material for this from: Highly Available Transactions: Virtues and Limitations, and Linearizability ... Continue Reading

the morning paper

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

Uncategorized