本文共 3790 字，大约阅读时间需要 12 分钟。

作者：chen_h

1.【会议】Bayesian Deep Learning

简介：

While deep learning has been revolutionary for machine learning, most modern deep learning models cannot represent their uncertainty nor take advantage of the well studied tools of probability theory. This has started to change following recent developments of tools and techniques combining Bayesian approaches with deep learning. The intersection of the two fields has received great interest from the community over the past few years, with the introduction of new deep learning models that take advantage of Bayesian techniques, as well as Bayesian models that incorporate deep learning elements [1-11]. In fact, the use of Bayesian techniques in deep learning can be traced back to the 1990s’, in seminal works by Radford Neal [12], David MacKay [13], and Dayan et al. [14]. These gave us tools to reason about deep models’ confidence, and achieved state-of-the-art performance on many tasks. However earlier tools did not adapt when new needs arose (such as scalability to big data), and were consequently forgotten. Such ideas are now being revisited in light of new advances in the field, yielding many exciting new results.

原文链接：

2.【博客】More than a Million Pro-Repeal Net Neutrality Comments were Likely Faked

简介：

NY Attorney General Schneiderman and used in spam campaigns that support repealing net neutrality. My research found at least 1.3 million fake pro-repeal comments, with suspicions about many more. In fact, the sum of fake pro-repeal comments in the proceeding may number in the millions. In this post, I will point out one particularly egregious spambot submission, make the case that there are likely many more pro-repeal spambots yet to be confirmed, and estimate the public position on net neutrality in the “organic” public submissions.

原文链接：

3.【博客】Thanksgiving Special ��: GANs are Being Fixed in More than One Way

简介：

In the spirit of thanksgiving, let me start by thanking all the active commenters on my blog: you are always very quick to point out typos, flaws and references to literature I overlooked.

This post is basically a follow-up my earlier post, ““. In this one, I review and recommend some additional references people pointed me to after the post was published. It turns out, unsurprisingly, that a lot more work on these questions than I was aware of. Although GANs are kind of broken, they are also actively being fixed, in more than one way.

原文链接：

4.【博客】A Visual Guide to Evolution Strategies

简介：

Neural network models are highly expressive and flexible, and if we are able to find a suitable set of model parameters, we can use neural nets to solve many challenging problems. Deep learning’s success largely comes from the ability to use the backpropagation algorithm to efficiently calculate the gradient of an objective function over each model parameter. With these gradients, we can efficiently search over the parameter space to find a solution that is often good enough for our neural net to accomplish difficult tasks.

原文链接：

5.【博客】Speeding up DQN on PyTorch: how to solve Pong in 30 minutes

简介：

Some time ago I’ve implemented all models from the article using PyTorch and my small RL library called PTAN. The code of if you’re curious.

To debug and test it I’ve used Pong game from Atari suite, mostly due to its simplicity, fast convergence, and hyperparameters robustness: you can use from 10 to 100 smaller size of replay buffer and it still will converge nicely. This is extremely helpful for a Deep RL enthusiast without access to the computational resources Google employees have. During implementation and debugging of the code, I was needed to run about 100–200 optimisations, so, it does matter how long one run takes: 2–3 days or just an hour.

原文链接：

转载地址：http://tldqb.baihongyu.com/