Hypercomplex-valued neural networks, including quaternion-valued neural networks, can treat multidimensional data as a single entity. In this paper, we present the quaternion-valued recurrent projection neural networks (QRPNNs). Briefly, QRPNNs are obtained by combining the non-local projection learning with the quaternion-valued recurrent correlation neural network (QRCNNs). We show that QRPNNs overcome the crosstalk problem of QRCNNs. Thus, they are appropriate to implement associative memories. Furthermore, computational experiments reveal that QRPNNs exhibit greater storage capacity and noise tolerance than their corresponding QRCNNs. Introduction The Hopfield neural network, developed in the early 1980s, is an important and widely-known recurrent neural network which can be used to implement associative memories [1, 2]. Successful applications of the Hopfield network include control [3, 4], computer vision and image processing [5, 6], classification [7, 8], and optimization [2, 9, 10]. Despite its many successful applications, the Hopfield network may suffer from a very low storage capacity when used to implement associative memories. Precisely, due to crosstalk between the stored items, the Hebbian learning adopted by Hopfield in his original work allows for the storage of approximately n/(2 ln n) items, where n denotes the length of the stored vectors [11]. For example, Personnaz et al. [12] as well as Kanter and Sompolinsky [13] proposed the projection rule to determine the synaptic weights of the Hopfield networks. The projection rule increases the storage capacity of the Hopfield network to n 1 items. Another simple but effective improvement on the storage capacity of the original Hopfield networks was achieved by Chiueh and Goodman's recurrent correlation neural networks (RCNNs) [14, 15]. Briefly, an RCNN is obtained by decomposing the Hopfield network with Hebbian learning into a two layer recurrent neural network.

Cosmic microwave background radiation (CMB) is critical to the understanding of the early universe and precise estimation of cosmological constants. Due to the contamination of thermal dust noise in the galaxy, the CMB map that is an image on the two-dimensional sphere has missing observations, mainly concentrated on the equatorial region. The noise of the CMB map has a significant impact on the estimation precision for cosmological parameters. Inpainting the CMB map can effectively reduce the uncertainty of parametric estimation. In this paper, we propose a deep learning-based variational autoencoder --- CosmoVAE, to restoring the missing observations of the CMB map. The input and output of CosmoVAE are square images. To generate training, validation, and test data sets, we segment the full-sky CMB map into many small images by Cartesian projection. CosmoVAE assigns physical quantities to the parameters of the VAE network by using the angular power spectrum of the Gaussian random field as latent variables. CosmoVAE adopts a new loss function to improve the learning performance of the model, which consists of $\ell_1$ reconstruction loss, Kullback-Leibler divergence between the posterior distribution of encoder network and the prior distribution of latent variables, perceptual loss, and total-variation regularizer. The proposed model achieves state of the art performance for Planck \texttt{Commander} 2018 CMB map inpainting.

Many classification applications require accurate probability estimates in addition to good class separation but often classifiers are designed focusing only on the latter. Calibration is the process of improving probability estimates by post-processing but commonly used calibration algorithms work poorly on small data sets and assume the classification task to be binary. Both of these restrictions limit their real-world applicability. Previously introduced Data Generation and Grouping algorithm alleviates the problem posed by small data sets and in this article, we will demonstrate that its application to multi-class problems is also possible which solves the other limitation. Our experiments show that calibration error can be decreased using the proposed approach and the additional computational cost is acceptable.

Academic research in the field of autonomous vehicles has reached high popularity in recent years related to several topics as sensor technologies, V2X communications, safety, security, decision making, control, and even legal and standardization rules. Besides classic control design approaches, Artificial Intelligence and Machine Learning methods are present in almost all of these fields. Another part of research focuses on different layers of Motion Planning, such as strategic decisions, trajectory planning, and control. A wide range of techniques in Machine Learning itself have been developed, and this article describes one of these fields, Deep Reinforcement Learning (DRL). The paper provides insight into the hierarchical motion planning problem and describes the basics of DRL. The main elements of designing such a system are the modeling of the environment, the modeling abstractions, the description of the state and the perception models, the appropriate rewarding, and the realization of the underlying neural network. The paper describes vehicle models, simulation possibilities and computational requirements. Strategic decisions on different layers and the observation models, e.g., continuous and discrete state representations, grid-based, and camera-based solutions are presented. The paper surveys the state-of-art solutions systematized by the different tasks and levels of autonomous driving, such as car-following, lane-keeping, trajectory following, merging, or driving in dense traffic. Finally, open questions and future challenges are discussed.

Juxi Leitner is co-founder of LYRO Robotics, a deep-tech startup based in Brisbane, Australia, creating robotic picking and packing solutions. LYRO is a spin-out of the Australian Centre of Excellence for Robotic Vision (ACRV), where Juxi is the research lead for the manipulation research stream (previously Vision and Action project). His research focus is on integrating Robotics, Computer Vision and Machine Learning/Artificial Intelligence (AI) for robust grasping and manipulation in real-world scenarios. In 2017 his team won the Amazon Robotics Challenge. Juxi is active in the local Brisbane deep-tech ecosystem and started Brisbane.AI and the Brisbane robotics interest group.

Artificial intelligence is being used in IVF to select embryos with the highest chance of resulting in a successful pregnancy. The AI algorithm, called Ivy, analyses time-lapse videos of embryos as they are incubated after being fertilised, and identifies which ones have the highest likelihood of successful development. It was developed by Harrison.ai, Women who undergo IVF using Ivy are informed about the algorithm and consent to its use.

"Roman" and I haven't exchanged words for about 10 seconds, but you wouldn't know it from the look on his face. This artificially intelligent avatar, a product of New Zealand-based Soul Machines, is supposed to offer human-like interaction by simulating the way our brains handle conversation. Roman can interpret facial expressions, generate expressions of his own, and converse on a variety of topics--making him what Soul Machines calls a "digital hero." Right now, though, Roman is glitching, stuck in a routine of blinking, furrowing his eyebrows, and twisting his mouth into a polite half-smile. Moments ago, he'd asked me what music I would beam into deep space if I were in charge of NASA, but my answer--the seminal modern jazz fusion tune "Lingus" by Snarky Puppy, of course--seems to have caught him off guard.

Telecoms have evolved quite well with the times and are likely to continue to do so. The coming years will present the biggest technology trends, and telecoms will have to navigate their benefits and challenges in 2020 and beyond. Whichever side of the tracks a telecommunications business emerges as a result of upcoming technology trends, good or bad, you can be certain that a telco revolution is at hand. From 5G to AI and beyond, telcos will be met with a new world that creates more industries to service. This new world will open doors to markets that once had no need for telecoms, creating many new opportunities.

Computers have guided us to the moon and back but can't help us with us with the biggest decisions we face today. Should Donald Trump be impeached? Should Britain leave the EU? Should Australia stop exporting fossil fuels? Questions like these do not have yes or no answers, however tempting it is to think otherwise.

Artificial Intelligence (AI) has the power to completely transform the way we do things, personally and in business. We have seen many cases of small businesses that have used AI to deliver exceptional services and products that go on to outshine the competition, or examples where businesses have completely revolutionised an internal process. In October, we saw tech startup Devika, work with their client Equalution (health-tech app) to deliver a better service to users. Implementing AI gave the body transformation platform customised health plans for users, based on their mindsets. In the long run it made the service provided much more effective and affordable. With all of these discussions and stories, our aim is to remove some of the "unknown" around AI. Today we're asking people in business "What does AI mean for your organisation?" Keep up to date with our stories LinkedIn, Twitter, Facebook and Instagram. The ability for artificial intelligence (AI) to learn and process massive amount of data will continue to grow as we make greater strides in computer processing power and deep learning algorithms.