The study was a success: the first two AIs learnt how to communicate securely from scratch. P input plaintext, K shared key, C encrypted text, and PEve and PBob are the computed plaintext outputs.The Google Brain team (which is based out in Mountain View and is separate from in London) started with three fairly vanilla neural networks called Alice, Bob, and Eve. Each neural network was given a very specific goal: Alice had to send a secure message to Bob; Bob had to try and decrypt the message; and Eve had to try and eavesdrop on the message and try to decrypt it. Alice and Bob have one advantage over Eve: they start with a shared secret key (i.e. this is symmetric encryption). Importantly, the AIs were not told how to encrypt stuff, or what crypto techniques to use: they were just given a loss function (a failure condition), and then they got on with it.

Brains have been associated with the field of artificial intelligence for more than half a century. The reason is simple: the brain is the best and perhaps only example we have of an intelligent system. But should the brain serve as mere inspiration or can it be a roadmap, providing the most efficient path to machine intelligence? More than 50 years ago artificial neural networks, or ANNs for short, were created with the intent of designing something that, like the brain, could learn without expert rules or human supervision. However, ANNs were designed at a time when little was known about how neurons worked in the brain.

Deep learning continues to gather steam in corporate computing, and IBM and Nvidia are teaming up to help accelerate the foundation behind artificial intelligence breakthroughs. The two companies are collaborating on a deep learning solution that melds technology from both companies in a bid to speed up the process of training computers to think and learn more like humans do. A new software toolkit available today called IBM PowerAI is designed to run on the recently announced IBM server built for artificial intelligence that features Nvidia NVLink technology optimized for IBM's Power Architecture. The hardware-software solution provides more than two times the performance of comparable servers with four graphics processing units (GPUs) running AlexNet with Caffe. The same four-GPU Power-based configuration running AlexNet with BVLC Caffe can also outperform 8-M40 GPU-based x86 configurations, making it the world's fastest commercially available enterprise systems platform on two versions of a key deep learning framework, the companies said.

IBM introduces Intu, new AI form which enables developers to embed supercomputer Watson functionality into numerous end-user devices, providing an advanced architecture for creating cognitive-enabled experiences. In IBM's speech, "cognitive computing" describes machine learning. The idea about Project Intu is that developers will have the chance to use the platform to embed the various machine learning features offered by IBM's Watson service into different applications and products, and make them work across a wide range of form variables. Intu makes easier the process for developers wanting to develop cognitive expertises in various form factors such as spaces, characters, bots or other IoT devices, and it extends cognitive techniques into the real world. The system enables devices to interact more naturally with users, causing different feelings and behaviors and making more significant and immersive experience for users.

Samsung Electronics Co. is making a drive for control of the car. The South Korean smartphone maker said Monday that it would buy U.S. auto-parts supplier Harman International Industries Inc., based in Stamford, Conn., for $8 billion in an all-cash deal that instantly makes Samsung a major player in the world of automotive technology. The deal -- Samsung's biggest acquisition in its history -- reshapes the pecking order in the global automotive supply chain, reflecting a quickening pace of innovation and an increased role for companies with deep pockets and a keen understanding of mobile services. Harman, an audio pioneer that dates back to 1953, has in recent years pushed aggressively into the automotive world under CEO Dinesh Paliwal, and has secured billions in new business, including big contracts with General Motors Co. and Fiat Chrysler Automobiles NV. It has projected an order backlog of $24 billion, more than three times annual revenue, and about two-thirds of its current sales come from auto makers.

BenevolentAI has acquired an exclusive licence for the novel clinical stage candidates, having first used its AI technology to assess their potential. It continues the firm's move into territory more often associated with IT heavyweights like Google and its DeepMind Health unit or IBM and its Watson technology. BenevolentAI's deal with J&J's Janssen Pharmaceutica NV company focuses on hard to treat diseases and will allow it to select a number of small molecule compounds, along with their patent portfolio. BenevolentAI will then have the sole right to develop, manufacture and commercialise these novel drug candidates in all indications and in all territories. The London-based firm said the agreement would enable it to accelerate its development pipeline and use its artificial intelligence technology to provide a rich source of clinical data.

IBM: AI Should Stand For'Augmented Intelligence' In response to a White House request for information about how to utilize artificial intelligence (AI) for the public good, IBM argues we should focus on a different sort of AI, augmented intelligence. In May, the White House Office of Science and Technology Policy announced a series of workshops focused on advances in AI, to explore the benefits and challenges of the technology, while also committing to the deployment of AI to improve government services. AI has made great strides in the past few years, after decades of unfulfilled promise. It's hard to find a major technology company today that isn't looking at AI-related disciplines like machine learning, natural language processing, image recognition, and neural networks as potential sources of growth, efficiency, and innovation. Everyone working with information technology, if not already dealing with some form of AI, can expect to be doing so soon.

TORONTO/OTTAWA – Officials say a Porter Airlines flight approaching Toronto's island airport took evasive action to avoid a suspected drone, injuring two flight attendants. Julie Leroux of Canada's Transportation Safety Board said the near collision occurred at 7:30 a.m. Leroux says the object involved in the near-miss was likely an unmanned aerial vehicle. Porter spokesman Brad Cicero says two flight attendants sustained minor injuries. They were taken to a hospital and released.

To encourage developers to build better chatbots, Seattle-based start-up, KITT.AI, has launched ChatFlow in private beta. ChatFlow framework makes it easier for developers to build better chatbots that can hold multi-turn conversations and work on multiple platforms. In 2015, Xuchen Yao was inspired to build KITT.AI when he realized there where "no good dialogue systems, and no good tools to create good dialogue systems," he said. KITT.AI originally focused on Amazon's Alexa platform, then received Amazon's Alexa Fund in 2015, and that's when Yao set out to build his talented team. How did the KITT.AI team meet?

I'm going to begin a multipart series of posts on Reinforcement Learning (RL) that roughly follow an old 1996 textbook "Reinforcement Learning An Introduction" by Sutton and Barto. From my research, this text still seems to be the most thorough introduction to RL I could find. The Barto & Sutton text is itself a great read and is fairly approachable even for beginners, but I still think it's worth breaking down even further. It still amazes me how most of machine learning theory was established decades ago yet we've seen a huge explosion of interest and use in just the past several years largely due to dramatic improvements in computational power (i.e.