**deeplearning**

Are Energy-Based GANs any more energy-based than normal GANs?

10 hours ago by ronert

EDIT: The post had a mistake, pretty crucial one, kindly pointed out by George Tucker, so the has changed from what it was in the original. I have falsely claimed that a variant of the general GAN algorithm is pathological, this turns out not to be the case. Sorry for the mistake.

Archive
deeplearning
machinelearning
10 hours ago by ronert

How powerful are Graph Convolutions? (review of Kipf & Welling, 2016)

10 hours ago by ronert

This post is about a paper that has just come out recently on practical generalizations of convolutional layers to graphs: Along the way I found this earlier, related paper: This post is mainly a review of (Kipf and Welling, 2016).

Archive
deeplearning
machinelearning
10 hours ago by ronert

InfoGAN: using the variational bound on mutual information (twice)

10 hours ago by ronert

Many people have recommended me the infoGAN paper, but I hadn't taken the time to read it until recently. It is actually quite cool: The InfoGAN idea is pretty simple. The paper presents an extension to the GAN objective.

Archive
deeplearning
machinelearning
10 hours ago by ronert

Understanding Minibatch Discrimination in GANs

10 hours ago by ronert

There was one idea in there which got me thinking, and this is what I wanted to write about here: minibatch discrimination. Here is the ipython/jupyter notebook I used to draw the plots and test some of the things in this post in practice.

Archive
deeplearning
10 hours ago by ronert

Dilated Convolutions and Kronecker Factored Convolutions

10 hours ago by ronert

These are my notes on an ICLR paper from this year: Whilst I wrote this note I also became aware of this paper: I think the two are related, but coming at the same thing from two different directions.

Archive
deeplearning
machinelearning
10 hours ago by ronert

Adversarial Preference Loss

10 hours ago by ronert

In my earlier post I talked about how the GAN training procedure can be modified slightly so it minimises $KL[Q\|P]$ divergence. I have also talked about how GANs can be understood as

Archive
deeplearning
10 hours ago by ronert

An Alternative Update Rule for Generative Adversarial Networks

10 hours ago by ronert

It is mentioned in the original GAN paper (Goodfellow et al, 2014) that the algorithm can be interpreted as minimising Jensen-Shannon divergence under some ideal conditions.

Archive
deeplearning
machinelearning
10 hours ago by ronert

Machine Learning is Fun Part 8: How to Intentionally Trick Neural Networks

yesterday by neuralmarket

Very nice! An hands-on guide in #keras to tricking a deep CNN using adversarial examples #DeepLearning

DeepLearning
keras
from twitter_favs
yesterday by neuralmarket

[1708.04987] ANI-1: A data set of 20M off-equilibrium DFT calculations for organic
molecules

2 days ago by dave_sullivan

RT @olexandr: We release biggest to date #compchem dataset of 20M #DFT calcs.Challenge your #MachineLearning #DeepLearning models!

compchem
DFT
MachineLearning
DeepLearning
from twitter
2 days ago by dave_sullivan

Twitter

2 days ago by jhill5

Why businesses need to take advantage of #BigData , #IoT & #AI now

#MachineLearning #DeepLearning #Fintech #ML #DL…

BigData
Fintech
AI
MachineLearning
IoT
DL
ML
DeepLearning
from twitter_favs
#MachineLearning #DeepLearning #Fintech #ML #DL…

2 days ago by jhill5