Our goal is to design architectures that retain the groundbreaking performance of Convolutional Neural Networks (CNNs) for landmark localization and at the same time are lightweight, compact and suitable for applications with limited computational resources. To this end, we make the following contributions: (a) we are the first to study the effect of neural network binarization on localization tasks, namely human pose estimation and face alignment. We exhaustively evaluate various design choices, identify performance bottlenecks, and more importantly propose multiple orthogonal ways to boost performance. (b) Based on our analysis, we propose a novel hierarchical, parallel and multi-scale residual architecture that yields large performance improvement over the standard bottleneck block while having the same number of parameters, thus bridging the gap between the original network and its binarized counterpart. (c) We perform a large number of ablation studies that shed light on the properties and the performance of the proposed block. (d) We present results for experiments on the most challenging datasets for human pose estimation and face alignment, reporting in many cases state-of-the-art performance. (e) We further provide additional results for the problem of facial part segmentation. Code can be downloaded from https://www.adrianbulat.com/binary-cnn-landmark

SciSports: Learning football kinematics through two-dimensional tracking data Anatoliy Babic, Harshit Bansal, Gianluca Finocchio, Julian Golak, Mark Peletier, Jim Portegies, Clara Stegehuis, Anuj Tyagi, Roland Vincze, William Weimin Yoo August 15, 2018 Abstract SciSports is a Dutch startup company specializing in football analytics. This paper describes a joint research effort with SciSports, during the Study Group Mathematics with Industry 2018 at Eindhoven, the Netherlands. The main challenge that we addressed was to automatically process empirical football players' trajectories, in order to extract useful information from them. The data provided to us was two-dimensional positional data during entire matches. We developed methods based on Newtonian mechanics and the Kalman filter, Generative Adversarial Nets and Variational Autoencoders. In addition, we trained a discriminator network to recognize and discern different movement patterns of players. The Kalman-filter approach yields an interpretable model, in which a small number of player-dependent parameters can be fit; in theory this could be used to distinguish among players. The Generative-Adversarial-Nets approach appears promising in theory, and some initial tests showed an improvement with respect to the baseline, but the limits in time and computational power meant that we could not fully explore it. We also trained a Discriminator network to distinguish between two players based on their trajectories; after training, the network managed to distinguish between some pairs of players, but not between others. After training, the Variational Autoencoders generated trajectories that are difficult to distinguish, visually, from the data. These experiments provide an indication that deep generative models can learn the underlying structure and statistics of football players' trajectories. This can serve as a starting point for determining player qualities based on such trajectory data. Keywords: Football, Trajectory, Newtonian mechanics, Kalman filter, Machine Learning, Generative Adversarial Nets, Variational Autoencoder, Discriminator 1 Introduction SciSports (http://www.scisports.com/) is a Dutch sports analytics company taking a data-driven approach to football. The company conducts scouting activities for football clubs, gives advice to football players about which football club might suit them best, and quantifies the abilities of football players through various performance metrics.

In many tasks, in particular in natural science, the goal is to determine hidden system parameters from a set of measurements. Often, the forward process from parameter- to measurement-space is a well-defined function, whereas the inverse problem is ambiguous: one measurement may map to multiple different sets of parameters. In this setting, the posterior parameter distribution, conditioned on an input measurement, has to be determined. We argue that a particular class of neural networks is well suited for this task -- so-called Invertible Neural Networks (INNs). Although INNs are not new, they have, so far, received little attention in literature. While classical neural networks attempt to solve the ambiguous inverse problem directly, INNs are able to learn it jointly with the well-defined forward process, using additional latent output variables to capture the information otherwise lost. Given a specific measurement and sampled latent variables, the inverse pass of the INN provides a full distribution over parameter space. We verify experimentally, on artificial data and real-world problems from astrophysics and medicine, that INNs are a powerful analysis tool to find multi-modalities in parameter space, to uncover parameter correlations, and to identify unrecoverable parameters.

The biological plausibility of the backpropagation algorithm has long been doubted by neuroscientists. Two major reasons are that neurons would need to send two different types of signal in the forward and backward phases, and that pairs of neurons would need to communicate through symmetric bidirectional connections. We present a simple two-phase learning procedure for fixed point recurrent networks that addresses both these issues. In our model, neurons perform leaky integration and synaptic weights are updated through a local mechanism. Our learning method generalizes Equilibrium Propagation to vector field dynamics, relaxing the requirement of an energy function. As a consequence of this generalization, the algorithm does not compute the true gradient of the objective function, but rather approximates it at a precision which is proven to be directly related to the degree of symmetry of the feedforward and feedback weights. We show experimentally that our algorithm optimizes the objective function.

When Pearse Keane started using optical coherence tomography (OCT) scanners to peer to the back of a person's eye in Los Angeles a decade ago, the machines were relatively crude. "The devices were lower resolution, they had much slower image acquisition speeds," says Keane, a consultant ophthalmic surgeon at Moorfields Eye Hospital and researcher at University College, London. From 2007, Keane spent two years studying scans from OCT machines learning to diagnose eye conditions in patients and pick out the minute details which make up sight-threatening diseases. "It was very time consuming, laborious work," Keane says. OCT scans use light to quickly create high resolution, 3D images of the back of the eye.

Irvine Calif.-based Syntiant thinks it can use embedded flash memory to greatly reduce the amount of power needed to perform deep-learning computations. Austin, Tex.-based Mythic thinks it can use embedded flash memory to greatly reduce the amount of power needed to perform deep-learning computations. They both might be right. A growing crowd of companies is hoping to deliver chips that accelerate otherwise onerous deep learning applications, and to some degree they all have similarities because "these are solutions that are created by the shape of the problem," explains Mythic founder and CTO Dave Fick. When executed in a CPU, that problem is shaped like a traffic jam of data. A neural network is made up of connections and "weights" that denote how strong those connections are, and having to move those weights around so they can be represented digitally in the right place and time is the major energy expenditure in doing deep learning today.

Artificial intelligence is now as good as human doctors at spotting early signs of blindness, a new collaboration between DeepMind and the NHS has shown. The new a system can spot 50 eye problems including as age-related macular degeneration and diabetic eye disease with 94 per cent accuracy and even provide a diagnosis for the one in four cases when experts cannot reach a consensus. Doctors are hopeful that it will speed up treatment for people who can wait up to 16 weeks for tests, according to charities, because of current shortages in the NHS. To develop the algorithm, programmers at DeepMind were given access to thousands of eye-scans from Moorfields Eye Hospital which they used to train their system to spot dozens of diseases over 18 months. Dr Pearse Keane, consultant ophthalmologist at Moorfields said: "The AI technology we're developing is designed to prioritise patients who need to be seen and treated urgently by a doctor or eye care professional.

Step by step, condition by condition, AI systems are slowly learning to diagnose disease as well as any human doctor, and they could soon be working in a hospital near you. The latest example is from London, where researchers from Google's DeepMind subsidiary, UCL, and Moorfields Eye Hospital have used deep learning to create software that identifies dozens of common eye diseases from 3D scans and then recommends the patient for treatment. The work is the result of a multiyear collaboration between the three institutions. And while the software is not ready for clinical use, it could be deployed in hospitals in a matter of years. Those involved in the research described is as "ground-breaking."

AI is massively transforming our world, but there's one thing it cannot do: love. In a visionary talk, computer scientist Kai-Fu Lee details how the US and China are driving a deep learning revolution -- and shares a blueprint for how humans can thrive in the age of AI by harnessing compassion and creativity. "AI is serendipity," Lee says. "It is here to liberate us from routine jobs, and it is here to remind us what it is that makes us human."

A new machine-learning system is as good as the best human experts at detecting eye problems and referring patients for treatment, say scientists. The groundbreaking artificial intelligence system, developed by the AI-outfit DeepMind with Moorfields eye hospital NHS foundation trust and University College London, was capable of correctly referring patients with more than 50 different eye diseases for further treatment with 94% accuracy, matching or beating world-leading eye specialists. "The results of this pioneering research with DeepMind are very exciting and demonstrate the potential sight-saving impact AI could have for patients," said Prof Sir Peng Tee Khaw, the director of the NIHR Biomedical Research Centre at Moorfields eye hospital and the UCL Institute of Ophthalmology. The two-stage AI system takes a more human-like and intelligible approach to analysing the highly complex optical coherence tomography (OCT) scans of patient retinas. These are commonly used to triage patients with sight problems into four clinical categories: urgent, semi-urgent, routine and observation only.