Some of the tightest information-theoretic generalization bounds depend on the average information between the learned hypothesis and a single training example. However, these sample-wise bounds were derived only for expected generalization gap. We show that even for expected squared generalization gap no such sample-wise information-theoretic bounds exist. The same is true for PAC-Bayes and single-draw bounds. Remarkably, PAC-Bayes, single-draw and expected squared generalization gap bounds that depend on information in pairs of examples exist.

Intelligent robotic systems, such as autonomous vehicles (AVs), are typically architected in a modular fashion and comprised of modules performing detection, tracking, prediction, planning, and control, among others [1, 2, 3, 4, 5, 6, 7, 8]. Modular architectures are generally desirable because of their verifiability, interpretability and generalization performance; however, they also suffer from compounding errors, information bottlenecks, and integration challenges. A promising line of work tackling these issues focuses on making AV stacks more integrated (by relaxing inter-module interfaces) and data-driven (by optimizing modules jointly with respect to their downstream task). For example, in the context of AV perception, recent work has achieved substantial performance gains by jointly training tracking models with detection [9] and prediction models [10, 11]. To extend such a joint, data-driven approach to decision making, existing approaches replace hand-engineered components, e.g., planning and control algorithms, with deep neural networks [12, 13, 14]. As neural networks are differentiable, they can be optimized end-to-end for a final control objective; however, they offer weaker generalization, little to no interpretability or safety guarantees. We introduce DiffStack, a differentiable AV stack with modules for prediction, planning, and control that combines the benefits of modular and data-driven architectures (Figure 1). The prediction module in DiffStack is a learned neural network that predicts the future motion of agents; the planning and control modules are principled, hand-engineered algorithms that produce AV actions given the current world state and motion predictions. Importantly, our hand-engineered planning and control algorithms are differentiable, enabling the training of the upstream prediction module for a downstream control objective by backpropagating gradients through the algorithms.

South Korea 13.12 Sri Lanka 13.13 Thailand 13.14 Taiwan 13.15 Rest of Asia-Pacific 14 Competitive Landscape 14.1 Competitive Quadrant 14.2 Market Share Analysis 14.3 Strategic Initiatives 14.3.1 M&A and Investments 14.3.2

Proxymity is bringing technological innovation to the market infrastructure of a long -established sector--Proxy Voting, Shareholder Disclosure and Identification. Founded in London and spun out of Citi, from very beginning our mission focused on benefitting the whole eco system, rather than just one part or one player within it. This ethos is endorsed by investment from a unique and global consortium of the industry's most influential financial institutions. We currently serve 29 markets and are growing our global footprint fast. With offices in UK, Israel and Australia, our Proxymity Shareholder ID and Vote Connect products can serve all markets globally, with our flagship Vote Connect Total product providing complete end-to-end digital connectivity in 12 key markets around the world.

At Wander cafe in Auckland's Wynyard Quarter, someone at the next table is listening to Sean Gourley while he is being interviewed about artificial intelligence. After eavesdropping on the chat they get up, walk over to Gourley's table and tell him how scared they are. Gourley says most people think there is a 1% chance of war between China and the United States, but in his universe it is looking more like 50%. US defence and intelligence clients account for a large portion of the business Gourley's San Francisco-based artificial intelligence (AI) company, PrimerAI, does – and right now business is booming. READ MORE: * Keeping up with the machines, new supercomputer will be NZ's most powerful for AI * Kiwis need to think about what they want from the age of AI, report says * 'Google should not be in the business of war', says employee after it drops Pentagon AI contract * While artificial intelligence is tipped to be'as significant as electricity', it's not coming for your job, yet ...

Page layout analysis is a fundamental step in document processing which enables to segment a page into regions of interest. With highly complex layouts and mixed scripts, scholarly commentaries are text-heavy documents which remain challenging for state-of-the-art models. Their layout considerably varies across editions and their most important regions are mainly defined by semantic rather than graphical characteristics such as position or appearance. This setting calls for a comparison between textual, visual and hybrid approaches. We therefore assess the performances of two transformers (LayoutLMv3 and RoBERTa) and an objection-detection network (YOLOv5). If results show a clear advantage in favor of the latter, we also list several caveats to this finding. In addition to our experiments, we release a dataset of ca. 300 annotated pages sampled from 19th century commentaries.

Large language models have recently attracted significant attention due to their impressive performance on a variety of tasks. ChatGPT developed by OpenAI is one such implementation of a large, pre-trained language model that has gained immense popularity among early adopters, where certain users go to the extent of characterizing it as a disruptive technology in many domains. Understanding such early adopters' sentiments is important because it can provide insights into the potential success or failure of the technology, as well as its strengths and weaknesses. In this paper, we conduct a mixed-method study using 10,732 tweets from early ChatGPT users. We first use topic modelling to identify the main topics and then perform an in-depth qualitative sentiment analysis of each topic. Our results show that the majority of the early adopters have expressed overwhelmingly positive sentiments related to topics such as Disruptions to software development, Entertainment and exercising creativity. Only a limited percentage of users expressed concerns about issues such as the potential for misuse of ChatGPT, especially regarding topics such as Impact on educational aspects. We discuss these findings by providing specific examples for each topic and then detail implications related to addressing these concerns for both researchers and users.

The most widely studied explainable AI (XAI) approaches are unsound. This is the case with well-known model-agnostic explanation approaches, and it is also the case with approaches based on saliency maps. One solution is to consider intrinsic interpretability, which does not exhibit the drawback of unsoundness. Unfortunately, intrinsic interpretability can display unwieldy explanation redundancy. Formal explainability represents the alternative to these non-rigorous approaches, with one example being PI-explanations. Unfortunately, PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. Recently, it has been observed that the (absolute) rigor of PI-explanations can be traded off for a smaller explanation size, by computing the so-called relevant sets. Given some positive {\delta}, a set S of features is {\delta}-relevant if, when the features in S are fixed, the probability of getting the target class exceeds {\delta}. However, even for very simple classifiers, the complexity of computing relevant sets of features is prohibitive, with the decision problem being NPPP-complete for circuit-based classifiers. In contrast with earlier negative results, this paper investigates practical approaches for computing relevant sets for a number of widely used classifiers that include Decision Trees (DTs), Naive Bayes Classifiers (NBCs), and several families of classifiers obtained from propositional languages. Moreover, the paper shows that, in practice, and for these families of classifiers, relevant sets are easy to compute. Furthermore, the experiments confirm that succinct sets of relevant features can be obtained for the families of classifiers considered.

Compositional generalization is a basic mechanism in human language learning, which current neural networks struggle with. A recently proposed Disentangled sequence-to-sequence model (Dangle) shows promising generalization capability by learning specialized encodings for each decoding step. We introduce two key modifications to this model which encourage more disentangled representations and improve its compute and memory efficiency, allowing us to tackle compositional generalization in a more realistic setting. Specifically, instead of adaptively re-encoding source keys and values at each time step, we disentangle their representations and only re-encode keys periodically, at some interval. Our new architecture leads to better generalization performance across existing tasks and datasets, and a new machine translation benchmark which we create by detecting naturally occurring compositional patterns in relation to a training set. We show this methodology better emulates real-world requirements than artificial challenges.

Humans form mental images of 3D scenes to support counterfactual imagination, planning, and motor control. Our abilities to predict the appearance and affordance of the scene from previously unobserved viewpoints aid us in performing manipulation tasks (e.g., 6-DoF kitting) with a level of ease that is currently out of reach for existing robot learning frameworks. In this work, we aim to build artificial systems that can analogously plan actions on top of imagined images. To this end, we introduce Mental Imagery for Robotic Affordances (MIRA), an action reasoning framework that optimizes actions with novel-view synthesis and affordance prediction in the loop. Given a set of 2D RGB images, MIRA builds a consistent 3D scene representation, through which we synthesize novel orthographic views amenable to pixel-wise affordances prediction for action optimization. We illustrate how this optimization process enables us to generalize to unseen out-of-plane rotations for 6-DoF robotic manipulation tasks given a limited number of demonstrations, paving the way toward machines that autonomously learn to understand the world around them for planning actions.