Roundup Good morning – here's some machine-learning bits and bytes to kick start your week. If this sort of tech is right up your street, then perhaps check out our AI conference, M3, in London, England. Alibaba to make its own AI chips: Jack Ma, CEO and chairman of Alibaba, the giant Chinese e-commerce conglomerate, announced it will set up a new company to build a neural network accelerator chip. The hardware will be perform inference, the decision-making stage in which a trained network acts on incoming data and spits out, say, the type of objects in a photo or the age of someone from their picture. Ma said it was a "core technology" that China needed to develop itself if were to stop relying on US imports. Both countries are locked in a tit-for-tat trade tariff war, with the US slapping extra levies on billions of Chinese-built components coming into America – from aerospace parts to networking equipment.

The first human to live for 1,000 years may have already been born. Ben Goertzel, founder and CEO of artificial intelligence firm SingularityNET, sees a large-scale shift over the coming years as super-advanced machines predict how different drugs will interact with the body. Speaking with Inverse at the Human-Level Artificial Intelligence conference organized by GoodAI in Prague, Czech Republic, Goertzel said "it's pretty clear to me" that researcher Aubrey de Grey is correct in his assertion that the first thousand-year-old person is already alive. De Grey argues that scientists need to solve seven types of aging damage, which will enable humans to receive regular top-up treatments to extend their lifespan. "It's not even that extremely visionary in the view of what longevity freaks like Aubrey and I believe, because I think we could easily be 10 or 20 years away, or even five years away from something that would let most people who took the therapy extend the lifespan by say, 10 or 20 years beyond it would be otherwise," Goertzel says.

Algorithmic Justice League is a collective started that aims to remove human bias from AI algorithms that can result in exclusionary experiences and discriminatory practices. It focuses on 3 key areas 1) Highlight Algorithmic Bias through Media, Art, and Science 2) Provide Space for People to Voice Concerns and Experiences with Coded Bias, 3) Develop Practices for Accountability During the Design, Development, and Deployment of Coded Systems. AI Now Institute at New York University is an interdisciplinary research center dedicated to understanding the social implications of artificial intelligence. Their work focuses on four core domains: Rights & Liberties, Labor & Automation, Bias & Inclusion, Safety & Critical Infrastructure. AI Ethics Lab brings together researchers and practitioners from various disciplines to detect and solve issues related to ethical design in AI. Based in US and Turkey, the Lab offers a comprehensive approach to ethical design of AI-related technology.

Porsche has announced it is increasing its total investment in venture capital activities by €150 million for the next five years. By making this move, the German automobile manufacturer intends to gain access to new technologies, trends and business models. Porsche Ventures, being a strategic investor, is aiming to invest in business models that involve mobility, digital lifestyle and customer experience, along with futuristic technologies like AI, blockchain, VR and AR. The company is looking to invest in startups that are still nascent and in their growth phases. For instance, Porsche Ventures' latest investment includes Berlin-based start-up "Gapless" – a company that allows customers to digitally manage their vintage vehicles, including the entire vehicle history, and share this information with other users in a secure format that prevents forgery.

Human action recognition refers to automatic recognizing human actions from a video clip, which is one of the most challenging tasks in computer vision. In reality, a video stream is often weakly-annotated with a set of relevant human action labels at a global level rather than assigning each label to a specific video episode corresponding to a single action, which leads to a multi-label learning problem. Furthermore, there are a great number of meaningful human actions in reality but it would be extremely difficult, if not impossible, to collect/annotate video clips regarding all of various human actions, which leads to a zero-shot learning scenario. To the best of our knowledge, there is no work that has addressed all the above issues together in human action recognition. In this paper, we formulate a real-world human action recognition task as a multi-label zero-shot learning problem and propose a framework to tackle this problem. Our framework simultaneously tackles the issue of unknown temporal boundaries between different actions for multi-label learning and exploits the side information regarding the semantic relationship between different human actions for zero-shot learning. As a result, our framework leads to a joint latent embedding representation for multi-label zero-shot human action recognition. The joint latent embedding is learned with two component models by exploring temporal coherence underlying video data and the intrinsic relationship between visual and semantic domain. We evaluate our framework with different settings, including a novel data split scheme designed especially for evaluating multi-label zero-shot learning, on two weakly annotated multi-label human action datasets: Breakfast and Charades. The experimental results demonstrate the effectiveness of our framework in multi-label zero-shot human action recognition.

During recent years there has been an increased interest in stochastic adaptations of limited memory quasi-Newton methods, which compared to pure gradient-based routines can improve the convergence by incorporating second order information. In this work we propose a direct least-squares approach conceptually similar to the limited memory quasi-Newton methods, but that computes the search direction in a slightly different way. This is achieved in a fast and numerically robust manner by maintaining a Cholesky factor of low dimension. This is combined with a stochastic line search relying upon fulfilment of the Wolfe condition in a backtracking manner, where the step length is adaptively modified with respect to the optimisation progress. We support our new algorithm by providing several theoretical results guaranteeing its performance. The performance is demonstrated on real-world benchmark problems which shows improved results in comparison with already established methods.

Reinforcement learning refers to a group of methods from artificial intelligence where an agent performs learning through trial and error. It differs from supervised learning, since reinforcement learning requires no explicit labels; instead, the agent interacts continuously with its environment. That is, the agent starts in a specific state and then performs an action, based on which it transitions to a new state and, depending on the outcome, receives a reward. Different strategies (e.g. Q-learning) have been proposed to maximize the overall reward, resulting in a so-called policy, which defines the best possible action in each state. Mathematically, this process can be formalized by a Markov decision process and it has been implemented by packages in R; however, there is currently no package available for reinforcement learning. As a remedy, this paper demonstrates how to perform reinforcement learning in R and, for this purpose, introduces the ReinforcementLearning package. The package provides a remarkably flexible framework and is easily applied to a wide range of different problems. We demonstrate its use by drawing upon common examples from the literature (e.g. finding optimal game strategies).

Apple co-founder Steve Wozniak has lost faith in autonomous cars for the time being. Wozniak has flip-flopped in his opinions about the technology over the last few years. In May 2017 he claimed driverless technology is the'biggest, most obvious moonshot,' in current times, pointing to Tesla as the most promising company in that field. But just months later he did a 180, and said he doesn't'believe anything Elon Musk or Tesla says.' Now, Wozniak has doubled down on his doubts surrounding autonomous technology, stating at a recent event that he has'given up' on self-driving cars. Apple co-founder Steve Wozniak has lost faith in autonomous cars for the time being.

Image source: Glenfinnan Viaduct – aka "The Harry Potter Bridge" source Wikipedia – an apt analogy bridging the known to the unknown! In April this year, I posted about the seven books to grasp the mathematical foundations of data science which was one of my most popular posts ever. It demonstrated to me that there is a real need to understand the maths foundations behind Data Science. As part of my teaching at the University of Oxford(Data Science for Internet of Things), I have often encountered the same issue in working with participants. I am also personally interested in democratising AI knowledge, especially for the younger generation.

Physicist and thinker Stephen Hawking appeared on-stage at Web Summit in Lisbon, Portugal today via telepresence to warn humanity about the development of artificial intelligence. "AI could develop a will of its own," Hawking said in his signature computer-generated voice. "The rise of AI could be the worst or the best thing that has happened for humanity." AI and robots are already threatening millions of jobs, Hawking said, but can be used for pro-social purposes as well. That won't just happen by accident, however.