Deep generative models provide powerful tools for distributions over complicated manifolds, such as those of natural images. But many of these methods, including generative adversarial networks (GANs), can be difficult to train, in part because they are prone to mode collapse, which means that they characterize only a few modes of the true distribution. To address this, we introduce VEEGAN, which features a reconstructor network, reversing the action of the generator by mapping from data to noise. Our training objective retains the original asymptotic consistency guarantee of GANs, and can be interpreted as a novel autoencoder loss over the noise. In sharp contrast to a traditional autoencoder over data points, VEEGAN does not require specifying a loss function over the data, but rather only over the representations, which are standard normal by assumption. On an extensive set of synthetic and real world image datasets, VEEGAN indeed resists mode collapsing to a far greater extent than other recent GAN variants, and produces more realistic samples.

Compressive image recovery is a challenging problem that requires fast and accurate algorithms. Recently, neural networks have been applied to this problem with promising results. By exploiting massively parallel GPU processing architectures and oodles of training data, they can run orders of magnitude faster than existing techniques. However, these methods are largely unprincipled black boxes that are difficult to train and often-times specific to a single measurement matrix. It was recently demonstrated that iterative sparse-signal-recovery algorithms can be "unrolled" to form interpretable deep networks. Taking inspiration from this work, we develop a novel neural network architecture that mimics the behavior of the denoising-based approximate message passing (D-AMP) algorithm. We call this new network Learned D-AMP (LDAMP). The LDAMP network is easy to train, can be applied to a variety of different measurement matrices, and comes with a state-evolution heuristic that accurately predicts its performance. Most importantly, it outperforms the state-of-the-art BM3D-AMP and NLR-CS algorithms in terms of both accuracy and run time. At high resolutions, and when used with sensing matrices that have fast implementations, LDAMP runs over $50\times$ faster than BM3D-AMP and hundreds of times faster than NLR-CS.

While strong progress has been made in image captioning recently, machine and human captions are still quite distinct. This is primarily due to the deficiencies in the generated word distribution, vocabulary size, and strong bias in the generators towards frequent captions. Furthermore, humans - rightfully so - generate multiple, diverse captions, due to the inherent ambiguity in the captioning task which is not explicitly considered in today's systems. To address these challenges, we change the training objective of the caption generator from reproducing groundtruth captions to generating a set of captions that is indistinguishable from human written captions. Instead of handcrafting such a learning target, we employ adversarial training in combination with an approximate Gumbel sampler to implicitly match the generated distribution to the human one. While our method achieves comparable performance to the state-of-the-art in terms of the correctness of the captions, we generate a set of diverse captions that are significantly less biased and better match the global uni-, bi-and trigram distributions of the human captions.

Michael Li is founder and CEO at The Data Incubator. The company offers curriculum based on feedback from corporate and government partners about the technologies they are using and learning, for masters and PhDs. Below is a ranking of 23 open-source deep learning libraries that are useful for Data Science, based on Github and Stack Overflow activity, as well as Google search results. The table shows standardized scores, where a value of 1 means one standard deviation above average (average score of 0). For example, Caffe is one standard deviation above average in Github activity, while deeplearning4j is close to average.

"Introduction to TensorFlow [EuroPython 2017 - Talk - 2017-07-14 - Anfiteatro 1] [Rimini, Italy] Deep learning is at its peak, with scholars and startups releasing new amazing applications every other week, and TensorFlow is the main tool to work with it. In this talk, we will cover the explanation of core concepts of deep learning and TensorFlow totally from scratch, using simple examples and friendly visualizations. The talk will go through the next topics: • Why deep learning and what is it?

There is little doubt that Artificial Intelligence (AI) is transforming almost every facet of human life. How far this transformation will go and what the full ramifications for society will be are still unknown but this hasn't prevented people from making both optimistic and dire predictions. Elon Musk's call for AI regulation has been matched by equal calls for governments not to. One of the principle problems with AI has been the confusion that surrounds what it is exactly, and what it can and can't actually do. The single biggest problem in understanding AI however has been making it clear how current AI techniques (like deep learning) differ from human intelligence.

When you think of artificial intelligence (AI), the word "emotion" doesn't typically come to mind. But there's an entire field of research using AI to understand emotional responses to news, product experiences, movies, restaurants, and more. It's known as sentiment analysis, or emotion AI, and it involves analyzing views – positive, negative, or neutral – from written text to understand and gauge reactions. Sentiment analysis can be used for survey research, social media analyses, and tracking psychological trends. Picture software that scans articles, reviews, ratings, and social media posts to determine sentiment changes for hotel guests.

After the last post where carlos demonstrated his utter lack of knowledgability in statistics while attempting to comment on stats fundamentals, I was already disinclined to pay him any mind, and this post is equally devoid of real insight. Why are people like this writing textbooks?

I was planning agenda for my one hour talk. Conveying the learning paths, setting up the environment and explaining the important machine learning concepts finally made it to agenda after a lot of contemplation and thought. I initially thought about various ways this talk could have been done including - hands on python with linear regression, explaining linear regression in detail, or just sharing my learning journey that I went through past 18 months almost. But I wanted to start something that leaves the audience with lots of new information and questions to work on. Create curiosity and interest in them.