Last month, Filestack sponsored an AI meetup wherein I presented a brief introduction to reinforcement learning and evolutionary strategies. Beforehand, I had promised code examples showing how to beat Atari games using PyTorch. In reality, I did not have time for that kind of side project and so I found some other examples of training agents to play Flappy Bird using Keras, which were entertaining but not complete enough for me to recommend as a springboard for further exploration. Luckily, I recently found some time to develop the promised training scripts. Therefore, I would like to provide an in-depth look of how we can use the PyTorch-ES suite for training reinforcement agents in a variety of environments, including Atari games and OpenAI Gym simulations. In deep reinforcement learning that uses the Q-learning algorithm, which has become very popular, training an intelligent agent includes distinct phases for "observation" and "learning".

IBM today announced the launch of its Adversarial Robustness Toolbox for AI developers. The open-source kit contains everything a machine learning programmer needs to attack their own deep learning neural networks (DNN) to ensure they're able to withstand real-world conditions. The toolbox comes in the form of a code library which includes attack agents, defense utilities, and benchmarking tools that allow developers to integrate baked-in resilience to adversarial attacks. The company says it's the first of its kind. One of the biggest challenges with some of the existing models to defend against adversarial AI is they are very platform specific.

The term "Industrial Revolution" – here onwards "IR" describes the period in which there was a gradual shift of improving the process of manufacturing and distributing goods. The First IR took place from the 18th to 19th centuries in Europe and America. It was a period when mostly agrarian, rural societies became industrial and urban. The iron and textile industries, along with the development of the steam engine, played central roles in the IR. The Second IR took place between 1870 and 1914, just before World War I.

Note: This post was written together with the awesome Julian Eisenschlos and was originally published on the TensorFlow blog. Throughout this post we will show you how to classify text using Estimators in TensorFlow. Welcome to Part 4 of a blog series that introduces TensorFlow Datasets and Estimators. You don't need to read all of the previous material, but take a look if you want to refresh any of the following concepts. Part 1 focused on pre-made Estimators, Part 2 discussed feature columns, and Part 3 how to create custom Estimators. Here in Part 4, we will build on top of all the above to tackle a different family of problems in Natural Language Processing (NLP).

TensorFlow is quickly becoming the technology of choice for deep learning, because of how easy TF makes it to build powerful and sophisticated neural networks. The Google Cloud Platform is a great place to run TF models at scale, and perform distributed training and prediction. This is a comprehensive, from-the-basics course on TensorFlow and building neural networks. It assumes no prior knowledge of Tensorflow, all you need to know is basic Python programming.

Royal Academy of Engineering,UK under Newton Bhabha Fund has approved a nation wide initiative on "AI and deep learning Skilling and Research" . University college, London, Brunel and Bennett University are collaborators of the project.

Summary: GDPR carries many new data and privacy requirements including a "right to explanation". On the surface this appears to be similar to US rules for regulated industries. We examine why this is actually a penalty and not a benefit for the individual and offer some insight into the actual wording of the GDPR regulation which also offers some relief. GDPR is now just about 60 days away and there's plenty to pay attention to especially in getting and maintaining permission to use a subscriber's data. If you're just starting out in the EU there are some new third party offerings that promise to keep track of things for you (Integris, Kogni, and Waterline all emphasized this feature at the Strata Data San Jose conference this month).

We're living the middle of a golden data age where our best and brightest are leveraging Artificial Intelligence technologies to create self-driving cars, facial recognition tools, and smart assistants that straddle the line between science and science fiction. Now, these breakthroughs are only the beginning, which is why it pays to understand how they work now, so you can help pioneer the next wave of AI innovations. The Pay What You Want: AI & Deep Learning Bundle can kickstart your deep dive into this field, and it's available for a price you pick. Here's how the deal works: Simply pay what you want, and you'll instantly unlock one of the collection's e-learning resources. Beat the average price paid, and you'll get the remaining nine at no extra charge.

In a talk given today at the American Association for Cancer Research's annual meeting, Google researchers described a prototype of an augmented reality microscope that could be used to help physicians diagnose patients. When pathologists are analyzing biological tissue to see if there are signs of cancer -- and if so, how much and what kind -- the process can be quite time-consuming. And it's a practice that Google thinks could benefit from deep learning tools. The company, however, believes this microscope could allow groups with limited funds, such as small labs and clinics, or developing countries to benefit from these tools in a simple, easy-to-use manner. Google says the scope could "possibly help accelerate and democratize the adoption of deep learning tools for pathologists around the world." The microscope is an ordinary light microscope, the kind used by pathologists worldwide.

In recent years, an increasing popularity of deep learning model for intelligent condition monitoring and diagnosis as well as prognostics used for mechanical systems and structures has been observed. In the previous studies, however, a major assumption accepted by default, is that the training and testing data are taking from same feature distribution. Unfortunately, this assumption is mostly invalid in real application, resulting in a certain lack of applicability for the traditional diagnosis approaches. Inspired by the idea of transfer learning that leverages the knowledge learnt from rich labeled data in source domain to facilitate diagnosing a new but similar target task, a new intelligent fault diagnosis framework, i.e., deep transfer network (DTN), which generalizes deep learning model to domain adaptation scenario, is proposed in this paper. By extending the marginal distribution adaptation (MDA) to joint distribution adaptation (JDA), the proposed framework can exploit the discrimination structures associated with the labeled data in source domain to adapt the conditional distribution of unlabeled target data, and thus guarantee a more accurate distribution matching. Extensive empirical evaluations on three fault datasets validate the applicability and practicability of DTN, while achieving many state-of-the-art transfer results in terms of diverse operating conditions, fault severities and fault types.