There's a whole marketing industry out there trying to persuade the world to buy Australian lamb. But our latest international success story is a bit more digital – not to mention eldritch – than meaty. Cult of the Lamb, a video game about indoctrinating cute animals into your dark sect and then sacrificing them for greater power, has topped the sales charts on release (temporarily overthrowing the latest Spider-Man game on PC) and has hit more than a million units sold in a week, according to its publisher. "It's been pretty crazy!" says Julian Wilton, one of the three core members of the game's Melbourne- and UK-based developer, Massive Monster. Wilton first met fellow founders Jay Armstrong and James Pearmain on a forum dedicated to internet-based flash games over a decade ago.

Every weekday, The Detail makes sense of the big news stories. This week, we talked about the burgeoning concerns over artificial intelligence, talked to two former political party presidents about their hidden role, visited a food bank operating in the wealthy North Shore, looked at the fight to keep foot-and-mouth disease out of our farms, and finished the week with a new Supreme Court case trying to hold big corporations liable for contributing to climate change. Whakarongo mai to any episodes you might have missed. Artificial intelligence systems running rogue might seem like the stuff of science-fiction, but these systems are increasingly common in many high-tech elements of society, from self-driving cars to digital assistants, facial identification, Netflix recommendations, and much, much more. The capabilities of artificial intelligence are growing at pace; a pace that's outstripping regulatory frameworks.

As I write this, Amazon is announcing its purchase of iRobot, adding its room-mapping robotic vacuum technology to the company's existing home surveillance suite, the Ring doorbell and prototype aerial drone. This is in addition to Amazon already knowing what you order online, what websites you visit, what foods you eat and, soon, every last scrap of personal medical data you possess. The trend of our gadgets and infrastructure constantly, often invasively, monitoring their users shows little sign of slowing -- not when there's so much money to be made. Of course it hasn't been all bad for humanity, what with AI's help in advancing medical, communications and logistics tech in recent years. In his new book, Machines Behaving Badly: The Morality of AI, Scientia Professor of Artificial Intelligence at the University of New South Wales, Dr. Toby Walsh, explores the duality of potential that artificial intelligence/machine learning systems offer and, in the excerpt below, how to claw back a bit of your privacy from an industry built for omniscience. Published by La Trobe University Press. The Second Law of Thermodynamics states that the total entropy of a system – the amount of disorder – only ever increases.

This article proposes Convolutional Neural Network-based Auto Encoder (CNN-AE) to predict location-dependent rate and coverage probability of a network from its topology. We train the CNN utilising BS location data of India, Brazil, Germany, and the USA and compare its performance with stochastic geometry (SG) based analytical models. In comparison to the best-fitted SG-based model, CNN-AE improves the coverage and rate prediction errors by a margin of as large as $40\%$ and $25\%$ respectively. As an application, we propose a low complexity, provably convergent algorithm that, using trained CNN-AE, can compute locations of new BSs that need to be deployed in a network in order to satisfy pre-defined spatially heterogeneous performance goals.

Over the past decades, researchers had put lots of effort investigating ranking techniques used to rank query results retrieved during information retrieval, or to rank the recommended products in recommender systems. In this project, we aim to investigate searching, ranking, as well as recommendation techniques to help to realize a university academia searching platform. Unlike the usual information retrieval scenarios where lots of ground truth ranking data is present, in our case, we have only limited ground truth knowledge regarding the academia ranking. For instance, given some search queries, we only know a few researchers who are highly relevant and thus should be ranked at the top, and for some other search queries, we have no knowledge about which researcher should be ranked at the top at all. The limited amount of ground truth data makes some of the conventional ranking techniques and evaluation metrics become infeasible, and this is a huge challenge we faced during this project. This project enhances the user's academia searching experience to a large extent, it helps to achieve an academic searching platform which includes researchers, publications and fields of study information, which will be beneficial not only to the university faculties but also to students' research experiences.

Graph pre-training strategies have been attracting a surge of attention in the graph mining community, due to their flexibility in parameterizing graph neural networks (GNNs) without any label information. The key idea lies in encoding valuable information into the backbone GNNs, by predicting the masked graph signals extracted from the input graphs. In order to balance the importance of diverse graph signals (e.g., nodes, edges, subgraphs), the existing approaches are mostly hand-engineered by introducing hyperparameters to re-weight the importance of graph signals. However, human interventions with sub-optimal hyperparameters often inject additional bias and deteriorate the generalization performance in the downstream applications. This paper addresses these limitations from a new perspective, i.e., deriving curriculum for pre-training GNNs. We propose an end-to-end model named MentorGNN that aims to supervise the pre-training process of GNNs across graphs with diverse structures and disparate feature spaces. To comprehend heterogeneous graph signals at different granularities, we propose a curriculum learning paradigm that automatically re-weighs graph signals in order to ensure a good generalization in the target domain. Moreover, we shed new light on the problem of domain adaption on relational data (i.e., graphs) by deriving a natural and interpretable upper bound on the generalization error of the pre-trained GNNs. Extensive experiments on a wealth of real graphs validate and verify the performance of MentorGNN.

This paper presents Tyche, a Python library to facilitate probabilistic reasoning in uncertain worlds through the construction, querying, and learning of belief models. Tyche uses aleatoric description logic (ADL), which provides computational advantages in its evaluation over other description logics. Tyche belief models can be succinctly created by defining classes of individuals, the probabilistic beliefs about them (concepts), and the probabilistic relationships between them (roles). We also introduce a method of observation propagation to facilitate learning from complex ADL observations. A demonstration of Tyche to predict the author of anonymised messages, and to extract author writing tendencies from anonymised messages, is provided. Tyche has the potential to assist in the development of expert systems, knowledge extraction systems, and agents to play games with incomplete and probabilistic information.

Neuralink, a company co-founded by Elon Musk, has been working on an implantable brain–machine interface since 2016. While it previously demonstrated its progress by showing a Macaque monkey controlling the cursor in a game of Pong, it has yet to start human trials. Now, according to Reuters, Musk has reached out to rival company Synchron in recent weeks to discuss a potential investment. It's unclear what kind of deal Musk has offered -- whether it's a collaboration or a financial investment --since none of the players responded or confirmed the report with the news organization. Reuters' sources also said that a deal isn't certain and that Synchron has yet to decide whether to accept Musk's offer.

Picking up transparent objects is still a challenging task for robots. The visual properties of transparent objects such as reflection and refraction make the current grasping methods that rely on camera sensing fail to detect and localise them. However, humans can handle the transparent object well by first observing its coarse profile and then poking an area of interest to get a fine profile for grasping. Inspired by this, we propose a novel framework of vision-guided tactile poking for transparent objects grasping. In the proposed framework, a segmentation network is first used to predict the horizontal upper regions named as poking regions, where the robot can poke the object to obtain a good tactile reading while leading to minimal disturbance to the object's state. A poke is then performed with a high-resolution GelSight tactile sensor. Given the local profiles improved with the tactile reading, a heuristic grasp is planned for grasping the transparent object. To mitigate the limitations of real-world data collection and labelling for transparent objects, a large-scale realistic synthetic dataset was constructed. Extensive experiments demonstrate that our proposed segmentation network can predict the potential poking region with a high mean Average Precision (mAP) of 0.360, and the vision-guided tactile poking can enhance the grasping success rate significantly from 38.9% to 85.2%. Thanks to its simplicity, our proposed approach could also be adopted by other force or tactile sensors and could be used for grasping of other challenging objects. All the materials used in this paper are available at https://sites.google.com/view/tactilepoking.

We propose a hybrid machine learning architecture that simultaneously employs multiple deep learning models analyzing contextual and behavioral characteristics of Windows portable executable, producing a final prediction based on a decision from the meta-model. The detection heuristic in contemporary machine learning Windows malware classifiers is typically based on the static properties of the sample since dynamic analysis through virtualization is challenging for vast quantities of samples. To surpass this limitation, we employ a Windows kernel emulation that allows the acquisition of behavioral patterns across large corpora with minimal temporal and computational costs. We partner with a security vendor for a collection of more than 100k int-the-wild samples that resemble the contemporary threat landscape, containing raw PE files and filepaths of applications at the moment of execution. The acquired dataset is at least ten folds larger than reported in related works on behavioral malware analysis. Files in the training dataset are labeled by a professional threat intelligence team, utilizing manual and automated reverse engineering tools. We estimate the hybrid classifier's operational utility by collecting an out-of-sample test set three months later from the acquisition of the training set. We report an improved detection rate, above the capabilities of the current state-of-the-art model, especially under low false-positive requirements. Additionally, we uncover a meta-model's ability to identify malicious activity in validation and test sets even if none of the individual models express enough confidence to mark the sample as malevolent. We conclude that the meta-model can learn patterns typical to malicious samples from representation combinations produced by different analysis techniques. We publicly release pre-trained models and anonymized dataset of emulation reports.