Hosted by Eleanor Drage and Kerry McInerney, The Good Robot is a podcast which explores the many complex intersections between gender, feminism and technology. In this episode, Eleanor talks to Alexander Thomas, a filmmaker and academic who leads the BA in Media Production at the University of East London. They discuss his new book about transhumanism, a philosophical movement that aims to improve human capabilities through technology and whose followers includes Jeff Bezos, Elon Musk, Larry Page, and also apparently the DJ Steve Aoki. Alex is himself one of the foremost commentators on transhumanism. He explores transhumanist fantasies about the future of the human, is obsessed with the extremes of possibility: they either think that AI will bring us radical abundance or total extinction.

The paper addresses the classical network tomography problem of inferring local traffic given origin-destination observations. Focusing on large complex public transportation systems, we build a scalable model that exploits input-output information to estimate the unobserved link/station loads and the users' path preferences. Based on the reconstruction of the users' travel time distribution, the model is flexible enough to capture possible different path-choice strategies and correlations between users travelling on similar paths at similar times. The corresponding likelihood function is intractable for medium or large-scale networks and we propose two distinct strategies, namely the exact maximum-likelihood inference of an approximate but tractable model and the variational inference of the original intractable model. As an application of our approach, we consider the emblematic case of the London underground network, where a tap-in/tap-out system tracks the starting/exit time and location of all journeys in a day. A set of synthetic simulations and real data provided by Transport For London are used to validate and test the model on the predictions of observable and unobservable quantities.

Computational cognitive models are a fundamental tool in behavioral neuroscience.

In this paper, we introduce a novel MCMC sampler, PARNI-DAG, for a fully-Bayesian approach to the problem of structure learning under observational data. Under the assumption of causal sufficiency, the algorithm allows for approximate sampling directly from the posterior distribution on Directed Acyclic Graphs (DAGs). PARNI-DAG performs efficient sampling of DAGs via locally informed, adaptive random neighborhood proposal that results in better mixing properties. In addition, to ensure better scalability with the number of nodes, we couple PARNI-DAG with a pre-tuning procedure of the sampler's parameters that exploits a skeleton graph derived through some constraint-based or scoring-based algorithms. Thanks to these novel features, PARNI-DAG quickly converges to high-probability regions and is less likely to get stuck in local modes in the presence of high correlation between nodes in high-dimensional settings. After introducing the technical novelties in PARNI-DAG, we empirically demonstrate its mixing efficiency and accuracy in learning DAG structures on a variety of experiments.

We propose the Quantization Model of neural scaling laws, explaining both the observed power law dropoff of loss with model and data size, and also the sudden emergence of new capabilities with scale. We derive this model from what we call the Quantization Hypothesis, where network knowledge and skills are "quantized" into discrete chunks (quanta). We show that when quanta are learned in order of decreasing use frequency, then a power law in use frequencies explains observed power law scaling of loss.

However, symmetries provide fixed hard constraints on the functions a network can represent, need to be specified in advance, and can not be adapted. Our goal is to allow flexible symmetry constraints that can automatically be learned from data using gradients. Learning symmetry and associated weight connectivity structures from scratch is difficult for two reasons. First, it requires efficient and flexible parameterisations of layer-wise equivariances. Secondly, symmetries act as constraints and are therefore not encouraged by training losses measuring data fit. To overcome these challenges, we improve parameterisations of soft equivariance and learn the amount of equivariance in layers by optimising the marginal likelihood, estimated using differentiable Laplace approximations. The objective balances data fit and model complexity enabling layer-wise symmetry discovery in deep networks. We demonstrate the ability to automatically learn layer-wise equivariances on image classification tasks, achieving equivalent or improved performance over baselines with hard-coded symmetry.

Reachy 2 is touted as a "lab partner for the AI era." Director James Cameron attends the "Avatar: The Way Of Water" World Premiere at Odeon Luxe Leicester Square in 2022 in London, England. 'I'LL BE BACK': James Cameron's stance on artificial intelligence has evolved over the past few years, and he feels Hollywood needs to embrace it in a few different ways. MADE IN AMERICA: Nvidia on Monday announced plans to manufacture its artificial intelligence supercomputers entirely in the U.S. for the first time. RIDEABLE 4-LEGGED ROOT: Kawasaki Heavy Industries has introduced something that feels straight out of a video game: CORLEO, a hydrogen-powered, four-legged robot prototype designed to be ridden by humans.

When the sun is out, it's just about warm enough here in north-east London to read outside – which means it's time to crack out the best new science fiction and find a sheltered spot. I love the way the genre continues to tackle the biggest issues of our day, whether that's ageing or artificial intelligence. Top of my pile is Lucy Lapinska's look at how a robot might deal with being freed from human governance, but I'm also looking forward to Nick Harkaway's latest, set in a world where a drug can (for a huge price) stop you from ageing, but it will also make you grow very large. And I'm keen to try out Sayaka Murata's strange and disturbing vision of the future, Vanishing World. Amane lives in a society where children are conceived by artificial insemination and raised by parents in "clean", sexless marriages. When she and her husband hear about an experimental town where residents are selected at random to be artificially inseminated en masse and children are raised collectively and anonymously, they decide to try living there.

Ch Supt Dan Card from the Met, local policing commander for north-east London, said the force was committed to finding Kaliyah, and were using drone technology and boats as part of their "thorough search over a wide area". "Specialist officers are supporting Kaliyah's family through this deeply upsetting time and our thoughts go out to all those impacted by what has happened." He added: "I'd like to thank the members of public, our first-responding officers, and colleagues from other emergency services, as they responded rapidly to carry out a large-scale search during a highly pressurised and distressing time." The force is appealing for witnesses. The search on Monday involved boats and helicopters from HM Coastguard, the Royal National Lifeboat Institution and London Fire Brigade.

Language models (LMs) trained on vast quantities of unlabelled data have greatly advanced the field of natural language processing (NLP). In this study, we re-visit the widely accepted notion in NLP that continued pre-training LMs on task-related texts improves the performance of fine-tuning (FT) in downstream tasks. Through experiments on eight single-sentence tasks and eight sentence-pair tasks in both semi-supervised and fully-supervised settings, we find that conventional continued pre-training does not consistently provide benefits and can even be detrimental for sentence-pair tasks or when prompt-based FT is used. To tackle these issues, we propose Prompt-based Continued Pre-training (PCP), which combines the idea of instruction tuning with conventional continued pre-training. Our approach aims to improve the performance of prompt-based FT by presenting both taskrelated texts and prompt templates to LMs through unsupervised pre-training objectives before fine-tuning for the target task. Our empirical evaluations on 21 benchmarks demonstrate that the PCP consistently improves the performance of state-of-the-art prompt-based FT approaches (up to 20.1% absolute) in both semisupervised and fully-supervised settings, even with only hundreds of unlabelled examples. Additionally, prompt-based FT with the PCP outperforms state-of-theart semi-supervised approaches with greater simplicity, eliminating the need for an iterative process and extra data augmentation. Our further analysis explores the performance lower bound of the PCP and reveals that the advantages of PCP persist across different sizes of models and datasets.