Machine learning and vision startup Aquabyte announced Tuesday that it has raised $3.5 million in seed funding in order to build out a team of developers to refine its software, which is geared toward using machine learning and vision to reduce costs for fish farming. The round was co-led by Costanoa Ventures and New Enterprise Associates. Princeton University and other investors also participated in the round. The main purpose of the round is to help the company build out a team to develop its technology, both at its headquarters in San Francisco as well as Norway, where the company is working with pilot customers. The company is also focused on Norway because there's significantly more fish farming there than there is in the United States.

Controversial vlogger Logan Paul has knocked Zoella off the top spot as UK children's favourite YouTuber, according to a study. Paul was embroiled in a row earlier this year when he posted a video showing the body of an apparent suicide victim. His rise suggested children were seeking "edgier" content, said an analyst for research firm Childwise. It was likely children had been exposed to "shocking content", he added. The Childwise study looked at the media habits of 2,000 children in the UK aged five to 16.

Japanese manga artist Kazuo Umezu has won an award at one of Europe's largest comic festivals held in France for a comic featuring a robot that develops emotions, his publisher said Tuesday. The 81-year-old author of "Watashi wa Shingo" ("My Name is Shingo") was given the Heritage Award at the 45th Angouleme International Comics Festival held for four days through Sunday. The prize is awarded to the producer of a work that is worthy of being handed down to posterity. He became the third Japanese manga artist to win the award after Shigeru Mizuki and Kazuo Kamimura, according to the comic's publisher, Shogakukan Inc. "This is (an award) from France, which loves manga as art. I'm truly happy!" Umezu said in a statement.

You will have the opportunity to work alongside prominent researchers and engineers in Cambridge, UK, gaining skills and hands-on experience working on practical AI and machine learning problems that help tackle some of society's toughest challenges. The ideal candidate will have a passion for leveraging their expertise from computer science work and/or other technical fields to solve real-world challenges by applying artificial intelligence (AI) and machine learning. To apply for the 2018 Microsoft AI Residency Program, complete the application and submit the following items in one PDF or .doc: For questions related to this program, please contact AIResidency@microsoft.com. See here for information on AI residencies available in Redmond, US.

A killer whale has been taught to speak human words through her blowhole. Wikie, a 16-year-old female orca living in a French marine theme park, is able to copy words such as'hello', 'bye bye' and'Amy', as well as count to three. The sounds emerge as parrot-like squawks, shrill whistles or raspberries, but most are easily understandable as words. The killer whale was able to mimic the duration and pitch of human speech, coming close on three words to a'high-quality match'. Scroll down to hear Wikie'talk' Wikie (left) a 16-year-old female orca in a French marine theme park, is able to copy words such as'hello', 'bye bye' and'Amy', as well as count to three. A killer whale has been taught to speak human words through her blowhole.

It is easy to confuse the current geopolitical situation with that of the 1980s. The United States and Russia each accuse the other of interfering in domestic affairs. Russia has annexed territory over U.S. objections, raising concerns about military conflict. Any modern-day cold war would include cyberattacks and nuclear powers' involvement in allies' conflicts. As during the Cold War after World War II, nations are developing and building weapons based on advanced technology.

Leading experts in artificial intelligence (AI) debated whether machines can ever be truly creative during an event at Imperial College London. The panel debate was part of the Night of Ideas, a programme of free debates exploring the latest ideas behind issues central to our times organised by the Institut Français. Academics from Imperial and other London institutions, were joined by a director from Spotify to talk about their latest research involving AI and discussed the creativity potential of computer software. The experts debated how developments in AI were enabling machines to produce music and paintings but questioned whether this meant they were being truly creative and should be recognised as artists in their own right. Dr Aldo Faisal, from the Department of Bioengineering and Department of Computing, gave his thoughts on what is powering the AI revolution.

How will enterprises manage artificial intelligence deployments when most managers and executives don't understand the underlying models, data science, or technology? That question is almost haunting. Artificial intelligence (AI for short) is lumped together with big data, machine learning, and neural networks to create what equates to a technology buzzword orgy. And if you want another theme toss in cloud computing, which is the enabler for AI. Sure, we know AI is a bit hyped.

Incremental versions of batch algorithms are often desired, for increased time efficiency in the streaming data setting, or increased memory efficiency in general. In this paper we present a novel algorithm for incremental kernel PCA, based on rank one updates to the eigendecomposition of the kernel matrix, which is more computationally efficient than comparable existing algorithms. We extend our algorithm to incremental calculation of the Nystr\"om approximation to the kernel matrix, the first such algorithm proposed. Incremental calculation of the Nystr\"om approximation leads to further gains in memory efficiency, and allows for empirical evaluation of when a subset of sufficient size has been obtained.

Deep reinforcement learning (RL) methods generally engage in exploratory behavior through noise injection in the action space. An alternative is to add noise directly to the agent's parameters, which can lead to more consistent exploration and a richer set of behaviors. Methods such as evolutionary strategies use parameter perturbations, but discard all temporal structure in the process and require significantly more samples. Combining parameter noise with traditional RL methods allows to combine the best of both worlds. We demonstrate that both off- and on-policy methods benefit from this approach through experimental comparison of DQN, DDPG, and TRPO on high-dimensional discrete action environments as well as continuous control tasks. Our results show that RL with parameter noise learns more efficiently than traditional RL with action space noise and evolutionary strategies individually.