BBR: Congestion-based congestion control

March 31, 2017November 11, 2019 ~ Adrian Colyer ~ 8 Comments

BBR: Congestion-based congestion control Cardwell et al., ACM Queue Sep-Oct 2016 With thanks to Hossein Ghodse (@hossg) for recommending today's paper selection. This is the story of how members of Google's make-tcp-fast project developed and deployed a new congestion control algorithm for TCP called BBR (for Bandwidth Bottleneck and Round-trip propagation time), leading to 2-25x ... Continue Reading

Stochastic program optimization

March 30, 2017November 11, 2019 ~ Adrian Colyer ~ 9 Comments

Stochastic program optimization Schkufza et al., CACM 2016 Yesterday we saw that DeepCoder can find solutions to simple programming problems using a guided search. DeepCoder needs a custom DSL, and a maximum program length of 5 functions. In 'Stochastic program optimization' Schkufza et al. also use a search strategy to generate code that meets a ... Continue Reading

DeepCoder: Learning to write programs

March 29, 2017November 11, 2019 ~ Adrian Colyer ~ 1 Comment

DeepCoder: Learning to write programs Balog et al., ICLR 2017 I'm mostly trying to wait until the ICLR conference itself before diving into the papers to be presented there, but this particular paper follows nicely on from yesterday, so I've decided to bring it forward. In 'Large scale evolution of image classifiers' we saw how ... Continue Reading

Large-scale evolution of image classifiers

March 28, 2017November 11, 2019 ~ Adrian Colyer ~ 6 Comments

Large-scale evolution of image classifiers Real et al., 2017 I'm sure you noticed the bewildering array of network architectures in use when we looked at some of the top convolution neural network papers of the last few years last week (Part 1, Part2, Part 3). With sufficient training data, these networks can achieve amazing feats, ... Continue Reading

Ethically aligned design

March 27, 2017November 11, 2019 ~ Adrian Colyer ~ 1 Comment

The IEEE Global Initiative for Ethical Considerations in Artificial Intelligence and Autonomous Systems. Ethically Aligned Design: A Vision For Prioritizing Wellbeing With Artificial Intelligence And Autonomous Systems, Version 1. IEEE, 2016. http://standards.ieee.org/develop/indconn/ec/autonomous_systems.html. Something a little different for today... the IEEE recently put out a first version of their "Ethically Aligned Design" report for public ... Continue Reading

A miscellany of fun deep learning papers

March 24, 2017November 11, 2019 ~ Adrian Colyer ~ 2 Comments

To round out the week, I thought I'd take a selection of fun papers from the 'More papers from 2016' section of top 100 awesome deep learning papers list. Colorful image colorization, Zhang et al., 2016 Texture networks: feed-forward synthesis of textures and stylized images Generative visual manipulation on the natural image manifold, Zhu et ... Continue Reading

Recurrent Neural Network models

March 23, 2017November 11, 2019 ~ Adrian Colyer ~ 2 Comments

Today we're pressing on with the top 100 awesome deep learning papers list, and the section on recurrent neural networks (RNNs). This contains only four papers (joy!), and even better we've covered two of them previously (Neural Turing Machines and Memory Networks, the links below are to the write-ups). That leaves up with only two ... Continue Reading

Convolution neural networks, Part 3

March 22, 2017November 11, 2019 ~ Adrian Colyer ~ 4 Comments

Today we're looking at the final four papers from the 'convolutional neural networks' section of the 'top 100 awesome deep learning papers' list. Deep residual learning for image recognition, He et al., 2016 Identity mappings in deep residual networks, He et al., 2016 Inception-v4, inception-resnet and the impact of residual connections or learning, Szegedy et ... Continue Reading

Convolution neural nets, Part 2

March 21, 2017November 11, 2019 ~ Adrian Colyer ~ 6 Comments

Today it's the second tranche of papers from the convolutional neural nets section of the 'top 100 awesome deep learning papers' list: Return of the devil in the details: delving deep into convolutional nets, Chatfield et al., 2014 Spatial pyramid pooling in deep convolutional networks for visual recognition, He et al., 2014 Very deep convolutional ... Continue Reading

Convolutional neural networks, Part 1

March 20, 2017November 11, 2019 ~ Adrian Colyer ~ 5 Comments

Having recovered somewhat from the last push on deep learning papers, it's time this week to tackle the next batch of papers from the 'top 100 awesome deep learning papers.' Recall that the plan is to cover multiple papers per day, in a little less depth than usual per paper, to give you a broad ... Continue Reading

the morning paper

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

Month: March 2017