Generative Adversarial Networks (GANs) are a class of deep generative models which aim to learn a target distribution in an unsupervised fashion. While they were successfully applied to many problems, training a GAN is a notoriously challenging task and requires a significant amount of hyperparameter tuning, neural architecture engineering, and a non-trivial amount of "tricks". The success in many practical applications coupled with the lack of a measure to quantify the failure modes of GANs resulted in a plethora of proposed losses, regularization and normalization schemes, and neural architectures. In this work we take a sober view of the current state of GANs from a practical perspective. We reproduce the current state of the art and go beyond fairly exploring the GAN landscape. We discuss common pitfalls and reproducibility issues, open-source our code on Github, and provide pre-trained models on TensorFlow Hub.

DataTalk is a fun show featuring data science leaders from around the world. We talk about artificial intelligence, machine learning, deep learning, computer vision, data visualizations, data ethics, data philanthropy, and much more.

We believe you should be able to get the books you need, when you need them, in the way you want. The best part about liveBook is that you already have it! Over 350 Manning books are available now in liveBook. To read the books you already own, you just click the liveBook link beside any book in your Manning account.

Net Promoter Score (NPS) has become a KPI at many organizations, and for good reason. It is simple to measure and has the distinctive ability to indicate how the business will perform on several other metrics, including customer retention and revenue. While NPS is easy to measure, it is difficult to improve. Organizations understand that detractors have low NPS because they have had an unsatisfactory experience at some point in their customer journey. However, identifying where or when the unsatisfactory experience occurred is a challenge.

In early 2018, Facebook's AI researchers unveiled a deep learning system that can transform 2D photo and video images of people into 3D mesh models of those human bodies in motion. Last month, Facebook publicly shared the code for its "DensePose" technology, which could be used by Hollywood filmmakers and augmented reality game developers--but maybe also by those seeking to build a surveillance state. DensePose goes beyond basic object recognition. Besides detecting humans in pictures, it can also make 3D models of their bodies by estimating the positions of their torsos and limbs. Those models can then enable the technology to create real-time 3D recreations of human movement in 2D videos.

While modern digital cameras have made significant strides in shooting cleaner images at high ISOs, many photographers still do battle with image noise on a regular basis. Chip maker NVIDIA has just revealed a new technique, based on deep learning, that can quickly dispatch image noise. As NVIDIA explains, typical deep learning approaches have required training a neural network to recognize when a clean end state image should look like based on a series of noisy images. Armed with this information, the network can then take a fresh, noisy image and remove the noise. But NVIDIA's new technique works without needing to be feed samples of noisy images. "It is possible to learn to restore signals without ever observing clean ones, at performance sometimes exceeding training using clean exemplars," the researchers stated in their paper.

Controversy arose not long ago when it became clear that Google had provided its TensorFlow APIs to the US Department of Defense's Project Maven. Google's assistance was needed to flag images from hours of drone footage for analyst review. There is clearly an ethical debate about the acceptability of appropriating ML for military uses. More broadly, there is also an important debate about the unintended consequences of ML that has not been weaponized but simply behaves unexpectedly, which results in damage or loss. Adding ML to a system inevitably introduces a black box and that generates risks.

What if you could take your photos that were originally taken in low light and automatically remove the noise and artifacts? Have grainy or pixelated images in your photo library and want to fix them? This deep learning-based approach has learned to fix photos by simply looking at examples of corrupted photos only. The work was developed by researchers from NVIDIA, Aalto University, and MIT, and is being presented at the International Conference on Machine Learning in Stockholm, Sweden this week. Recent deep learning work in the field has focused on training a neural network to restore images by showing example pairs of noisy and clean images.

I want to thank Dan and Alex for all the help and effort in providing the data and details. This was a live project with live data. Dan and Alex provided the most detailed information on the data-sets and with their huge expertise and experience on the subject matter, I had no issues understanding and augmenting the business meaning. Time-series data is always tricky, the change of value with time is not constant with time with is a functional derivation of many variables. The time itself is not stationary and can have both a positive and negative impact on the outcome.

General Motors deployed the first mechanical-arm robot to operate one of its assembly lines as early as 1959. Since that time, robots have been employed to perform numerous manufacturing tasks such as welding, riveting, and painting. This first generation of robots was inflexible, could not respond simply to errors, and required individual programming specific to the tasks they were designed to perform. These robots were governed and inspired by logic--a series of programs coded into their operating systems. Now, the next wave of intelligent robotics is taking advantage of a different kind of learning, predicated on experience rather than logical instruction, to learn how to perform tasks in much the same way that a child would.