We show how to control the generalization error of time series models wherein past values of the outcome are used to predict future values. The results are based on a generalization of standard i.i.d. concentration inequalities to dependent data without the mixing assumptions common in the time series setting. Our proof and the result are simpler than previous analyses with dependent data or stochastic adversaries which use sequential Rademacher complexities rather than the expected Rademacher complexity for i.i.d. processes. We also derive empirical Rademacher results without mixing assumptions resulting in fully calculable upper bounds.

We propose a partially learned approach for the solution of ill posed inverse problems with not necessarily linear forward operators. The method builds on ideas from classical regularization theory and recent advances in deep learning to perform learning while making use of prior information about the inverse problem encoded in the forward operator, noise model and a regularizing functional. The method results in a gradient-like iterative scheme, where the "gradient" component is learned using a convolutional network that includes the gradients of the data discrepancy and regularizer as input in each iteration. We present results of such a partially learned gradient scheme on a non-linear tomographic inversion problem with simulated data from both the Sheep-Logan phantom as well as a head CT. The outcome is compared against FBP and TV reconstruction and the proposed method provides a 5.4 dB PSNR improvement over the TV reconstruction while being significantly faster, giving reconstructions of 512 x 512 volumes in about 0.4 seconds using a single GPU.

We propose a novel approximate inference algorithm that approximates a target distribution by amortising the dynamics of a user-selected MCMC sampler. The idea is to initialise MCMC using samples from an approximation network, apply the MCMC operator to improve these samples, and finally use the samples to update the approximation network thereby improving its quality. This provides a new generic framework for approximate inference, allowing us to deploy highly complex, or implicitly defined approximation families with intractable densities, including approximations produced by warping a source of randomness through a deep neural network. Experiments consider image modelling with deep generative models as a challenging test for the method. Deep models trained using amortised MCMC are shown to generate realistic looking samples as well as producing diverse imputations for images with regions of missing pixels.

Based in the Big Apple itself (New York), Synechron is one of the fastest-growing digital, business consulting & technology services providers. Since they opened their doors in 2001, Synechron has been expanding at a rapid rate. They now operate in 18 countries around the the world, and has a marked presence in the US, Australia, Canada, UK, Japan, The Netherlands, Hong Kong, Singapore, UAE, Ireland, Germany, Switzerland, Luxembourg, Italy, France, and India. With the AI Summit London drawing ever closer (it's only one week away!), we spoke to Ben Musgrave, who is Synechron's Business Development Manager, in order to understand how one of the event's key sponsors is deploying AI today and how they plan to in the future. We started off our conversation with Musgrave – who'll be delivering a keynote speech at the AI Summit London – how they are currently involved in the AI-space.

In this article, I cover the 12 types of AI problems i.e. I address the question: in which scenarios should you use Artificial Intelligence (AI)? Recently, I conducted a strategy workshop for a group of senior executives running a large multi national. In the workshop, one person asked the question: How many cats does it need to identify a Cat? This question is in reference to Andrew Ng's famous paper on Deep Learning where he was correctly able to identify images of Cats from YouTube videos.

It is no doubt that the sub-field of machine learning / artificial intelligence has increasingly gained more popularity in the past couple of years. As Big Data is the hottest trend in the tech industry at the moment, machine learning is incredibly powerful to make predictions or calculated suggestions based on large amounts of data. Some of the most common examples of machine learning are Netflix's algorithms to make movie suggestions based on movies you have watched in the past or Amazon's algorithms that recommend books based on books you have bought before. So if you want to learn more about machine learning, how do you start? For me, my first introduction is when I took an Artificial Intelligence class when I was studying abroad in Copenhagen. My lecturer is a full-time Applied Math and CS professor at the Technical University of Denmark, in which his research areas are logic and artificial, focusing primarily on the use of logic to model human-like planning, reasoning and problem solving.

Last week, at an event on AI, I asked the panel about how investors evaluate the Data readiness of AI start-ups. This subject is close to my work and my teaching. I teach a course on Implementing Enterprise AI and also teach Data Science for IoT at the University of Oxford. Professor Neil Laurence has proposed a concept of Data readiness levels. The highest level of Data readiness represents Data which is most useful to make predictions i.e. "Can we use this data to prove the efficacy of a drug?"

The longer you spend with the entrepreneurs behind the video game industry cluster in Cambridge, the more the forthcoming general election begins to seem a trifling, parochial concern. Compared with the momentous significance of the vote to leave the EU, next month's election barely registers for people such as Mark Gerhard, CEO of Playfusion, a video game company (pictured above) employing 58 people, of whom about 60% are from the EU. Almost all of us are disengaged from it. The cruel thing is that it doesn't affect us; if it goes really bad we can change our situation, we can solve it," he says. For people working in Cambridge's science parks, part of the hi-tech, global knowledge economy, the fallout from the Brexit vote is still the key political issue. Cambridge voted 74% to remain, and the shock of seeing things not go their way remains palpable. Bosses and senior employees in this tech cluster are highly educated and relatively well-off, and have many choices about where they base themselves. For the moment, this is Cambridge, but many are watching and waiting, contemplating their next steps, ready to leave the country should things turn unfavourable. In the months after the Brexit vote, Gerhard (who is originally from South Africa, but has lived here for 19 years and now has citizenship) was so dismayed to feel, as an immigrant, like he no longer belonged, that he contemplated moving to America. The election of Trump put paid to that idea, he says, but he is clear that should Brexit-related developments make it harder for his company to thrive in the UK, he will relocate. "It's not a threat; the reality is that for highly skilled individuals, the world is borderless.

Technology / What countries are investing in robots? A recent study by Redwood Software and the Centre for Economic and Business Research (Cebr) has focused on the impact of robotics automation on economic development across OECD countries, including the UK and the US. How does UK robotics investment compare to other countries? The report found that the UK has a much smaller robotics investment/GDP share in comparison to Japan, Germany and the US. Expressed in 2015 PPP (Purchasing Power Parity) terms, robotics investment in the US was $86billion in 2015, approximately 62 times that of the UK, recovering strongly from less than $30billion during the recession in 2009.

This document is written with the intention to describe in detail a method and means by which a computer program can reason about the world and in so doing, increase its analogue to a living system. As the literature is rife and it is apparent we, as scientists and engineers, have not found the solution, this document will attempt the solution by grounding its intellectual arguments within tenets of human cognition in Western philosophy. The result will be a characteristic description of a method to describe an artificial system analogous to that performed for a human. The approach was the substance of my Master's thesis, explored more deeply during the course of my postdoc research. It focuses primarily on context awareness and choice set within a boundary of available epistemology, which serves to describe it. Expanded upon, such a description strives to discover agreement with Kant's critique of reason to understand how it could be applied to define the architecture of its design. The intention has never been to mimic human or biological systems, rather, to understand the profoundly fundamental rules, when leveraged correctly, results in an artificial consciousness as noumenon while in keeping with the perception of it as phenomenon.