Opening the black box of deep neural networks via information – Part II

November 16, 2017 ~ Adrian Colyer ~ 5 Comments

Opening the black box of deep neural networks via information Schwartz-Viz & Tishby, ICRI-CI 2017 Yesterday we looked at the information theory of deep learning, today in part II we’ll be diving into experiments using that information theory to try and understand what is going on inside of DNNs. The experiments are done on a ... Continue Reading

Opening the black box of deep neural networks via information – part I

November 15, 2017 ~ Adrian Colyer ~ 23 Comments

Opening the black box of deep neural networks via information Schwartz-Viz & Tishby, ICRI-CI 2017 In my view, this paper fully justifies all of the excitement surrounding it. We get three things here: (i) a theory we can use to reason about what happens during deep learning, (ii) a study of DNN learning during training ... Continue Reading

Matrix capsules with EM routing

November 14, 2017 ~ Adrian Colyer ~ 7 Comments

Matrix capsules with EM routing Anonymous ;), Submitted to ICLR’18 (Where we know anonymous to be some combination of Hinton et al.). This is the second of two papers on Hinton’s capsule theory that has been causing recent excitement. We looked at ‘Dynamic routing between capsules’ yesterday, which provides some essential background so if you’ve ... Continue Reading

Dynamic routing between capsules

November 13, 2017 ~ Adrian Colyer ~ 3 Comments

Dynamic routing between capsules Sabour et al., NIPS’17 The Morning Paper isn’t trying to be a ‘breaking news’ site (there are plenty of those already!) — we covered a paper from 1950 last month for example! That said, when exciting research news breaks, of course I’m interested to read up on it. So The Morning ... Continue Reading

A model for reasoning about JavaScript promises

November 10, 2017 ~ Adrian Colyer ~ 1 Comment

A model for reasoning about JavaScript promises§ Madsen et al., OOPSLA’17 As an antidote to callback-hell, ECMAScript 6 introduces Promises. Promises represent the value of an asynchronous computation, and the functions resolve and reject are used to settle the promise. Promises can be chained using then. However, the semantics of JavaScript promises are quite complex, ... Continue Reading

Type test scripts for TypeScript testing

November 9, 2017 ~ Adrian Colyer ~ 2 Comments

Type test scripts for TypeScript testing Kristensen et al., OOPLSA’17 Today’s edition of The Morning Paper comes with a free tongue-twister; ‘type test scripts for TypeScript testing!’ One of the things that people really like about TypeScript is the DefinitelyTyped repository of type declarations for common (otherwise untyped) JavaScript libraries. There are over 3000 such ... Continue Reading

Fast and precise type checking for JavaScript

November 8, 2017 ~ Adrian Colyer ~ 3 Comments

Fast and precise type checking for JavaScript Chaudhuri et al., OOPSLA’17 In this paper we present the design and implementation of Flow, a fast and precise type checker for JavaScript that is used by thousands of developers on millions of lines of code at Facebook every day. In a pretty dense 30 pages, ‘Fast and ... Continue Reading

Virtual machine warmup blows hot and cold

November 7, 2017 ~ Adrian Colyer ~ 4 Comments

Virtual machine warmup blows hot and cold Barrett et al., OOPSLA’17 (With thanks to Prof. Richard Jones at Kent University who first pointed this paper out to me.) Yesterday we saw the recommendations of Georges et al. for determining when a (Java) virtual machine has reached a steady state and benchmarks can be taken. Kalibera ... Continue Reading

Statistically rigorous Java performance evaluation

November 6, 2017 ~ Adrian Colyer ~ 16 Comments

Statistically rigorous Java performance evaluation Georges et al., OOPSLA’07 This paper won the 10-year most influential paper award at OOPSLA this year. Many of the papers we look at on this blog include some kind of performance evaluation. As Georges et al., show, without good experimental design and statistical rigour it can be hard to ... Continue Reading

Log20: Fully automated optimal placement of log printing statements under specified overhead threshold

November 3, 2017 ~ Adrian Colyer ~ 15 Comments

Log20: Fully automated optimal placement of log printing statements under specified overhead threshold Zhao et al., SOSP’17 Logging has become an overloaded term. In this paper logging is used in the context of recording information about the execution of a piece of software, for the purposes of aiding troubleshooting. For these kind of logging statements ... Continue Reading

the morning paper

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

Month: November 2017