There has been increasing interest in characterising the error behaviour of systems which contain deep learning models before deploying them into any safety-critical scenario. However, characterising such behaviour usually requires large-scale testing of the model that can be extremely computationally expensive for complex real-world tasks. For example, tasks involving compute intensive object detectors as one of their components. In this work, we propose an approach that enables efficient large-scale testing using simplified low-fidelity simulators and without the computational cost of executing expensive deep learning models. Our approach relies on designing an efficient surrogate model corresponding to the compute intensive components of the task under test. We demonstrate the efficacy of our methodology by evaluating the performance of an autonomous driving task in the Carla simulator with reduced computational expense by training efficient surrogate models for PIXOR and CenterPoint LiDAR detectors, whilst demonstrating that the accuracy of the simulation is maintained.

In collaborative filtering, it is an important way to make full use of social information to improve the recommendation quality, which has been proved to be effective because user behavior will be affected by her friends. However, existing works leverage the social relationship to aggregate user features from friends' historical behavior sequences in a user-level indirect paradigm. A significant defect of the indirect paradigm is that it ignores the temporal relationships between behavior events across users. In this paper, we propose a novel time-aware sequential recommendation framework called Social Temporal Excitation Networks (STEN), which introduces temporal point processes to model the fine-grained impact of friends' behaviors on the user s dynamic interests in an event-level direct paradigm. Moreover, we propose to decompose the temporal effect in sequential recommendation into social mutual temporal effect and ego temporal effect. Specifically, we employ a social heterogeneous graph embedding layer to refine user representation via structural information. To enhance temporal information propagation, STEN directly extracts the fine-grained temporal mutual influence of friends' behaviors through the mutually exciting temporal network. Besides, the user s dynamic interests are captured through the self-exciting temporal network. Extensive experiments on three real-world datasets show that STEN outperforms state-of-the-art baseline methods. Moreover, STEN provides event-level recommendation explainability, which is also illustrated experimentally.

This position paper highlights an ethic of machine-to-machine cooperation and machine pro-sociality, and argues that machines capable of autonomous sensing, decision-making and action, such as automated vehicles and urban robots, owned and used by different self-interested parties, and having their own agendas (or interests of their owners) should be designed and built to be cooperative in their behaviours, especially if they share public spaces. That is, by design, the machine should first cooperate, and then only consider alternatives if there are problems. It is argued that being cooperative is not only important for their improved functioning, especially, when they use shared resources (e.g., parking spaces, public roads, curbside space and walkways), but also as a favourable requirement analogous to how humans cooperating with other humans can be advantageous and often viewed favourably. The usefulness of such machine-to-machine cooperation are illustrated via examples including cooperative crowdsourcing, cooperative traffic routing and parking as well as futuristic scenarios involving urban robots for delivery and shopping. It is argued that just as privacy-by-design and security-by-design are important considerations, in order to yield systems that fulfil ethical requirements, cooperative-by-design should also be an imperative for autonomous systems that are separately owned but co-inhabit the same spaces and use common resources. If a machine using shared public spaces is not cooperative, as one might expect, then it is not only anti-social but not behaving ethically. It is also proposed that certification for urban robots that operate in public could be explored.

Recurrent Neural Network (RNN) is a fundamental structure in deep learning. Recently, some works study the training process of over-parameterized neural networks, and show that over-parameterized networks can learn functions in some notable concept classes with a provable generalization error bound. In this paper, we analyze the training and generalization for RNNs with random initialization, and provide the following improvements over recent works: 1) For a RNN with input sequence $x=(X_1,X_2,...,X_L)$, previous works study to learn functions that are summation of $f(\beta^T_lX_l)$ and require normalized conditions that $||X_l||\leq\epsilon$ with some very small $\epsilon$ depending on the complexity of $f$. In this paper, using detailed analysis about the neural tangent kernel matrix, we prove a generalization error bound to learn such functions without normalized conditions and show that some notable concept classes are learnable with the numbers of iterations and samples scaling almost-polynomially in the input length $L$. 2) Moreover, we prove a novel result to learn N-variables functions of input sequence with the form $f(\beta^T[X_{l_1},...,X_{l_N}])$, which do not belong to the ``additive'' concept class, i,e., the summation of function $f(X_l)$. And we show that when either $N$ or $l_0=\max(l_1,..,l_N)-\min(l_1,..,l_N)$ is small, $f(\beta^T[X_{l_1},...,X_{l_N}])$ will be learnable with the number iterations and samples scaling almost-polynomially in the input length $L$.

Dr Thaler's international crusade for recognition of machine inventorship (which I reported on last year) is nearing the end of the line in the UK. Last week, in Thaler v Comptroller General of Patents Trade Marks And Designs [2021] EWCA Civ 1374, the Court of Appeal upheld the rejection of his DABUS patent applications. In 2018, Dr Thaler, the owner of DABUS (an artificial intelligence ("AI") creativity machine) submitted two patent applications to the UKIPO naming himself as the owner and DABUS as the inventor. The UKIPO rejected his applications on the basis that, for the purposes of the Patents Act 1977 ("PA 1997"), the inventor must be a "person" (with legal personality, such as a human or a corporate entity), and considering how ownership is derived from inventorship, Dr Thaler could not be the owner in the absence of a valid inventor. In 2020, in the Court of First Instance, Marcus Smith J upheld the UKIPO's decision, concluding that section 7 PA 1997, which sets out the classes of persons to whom patents can be granted, could not be interpreted to cover non-legal persons such as machines. On that basis, he found that the UKIPO was entitled to withdraw Dr Thaler's application under section 13 PA 1997.

Today artificial intelligence (AI) driven digital technologies are giving us new pathways to always have your loved ones with you, 7x24. Not really, despite the eeriness from Black Mirror episodes, or Carrie Fisher digitally created to carry on as Princess Leia in Star Wars, and Microsoft securing a patent for software that could reincarnate people as a chat bot, opening the door to more uses of AI contemplating how to bring the dead back to life are rapidly accelerating. Are we ready for death resurrections? Is this the right thing for us to be doing? From my research, we don't have all the answers to this complex question yet, but what we have are many innovators, academics, researchers shaping the answer to this question that will enable richer immersive digital learning experiences – and others that bringing grandma back to life – and persisting forever – may feel positively therapeutic to ease a deep grief, or feel like you are immersed in a Stephen King movie.

In new research being undertaken by Flinders University in partnership with conservation charity Koala Life and the State Government, non-invasive koala monitoring techniques are being developed using drones and facial recognition technology to count, identify and re-identify koalas. Minister for Environment and Water David Speirs said this cutting-edge technology will be used as part of a study on koalas at Kangaroo Island and the Adelaide Mount Lofty Ranges to get a better understanding of both their numbers and their movements. "Traditionally, monitoring koala populations has involved capturing and individually marking koalas, a process that is both labour-intensive and poses potential welfare issues," Minister Speirs said. "It is very important for us to develop non-invasive techniques to help monitor animals in a safe way, and facial recognition through drone monitoring is utilising the latest technology to achieve this. "The ability to recognise individual members of a species in the wild will help to grow an understanding of individual movements as well as population estimates, and this understanding will allow the development of meaningful management strategies.

With the remarkable success of representation learning for prediction problems, we have witnessed a rapid expansion of the use of machine learning and deep learning for the analysis of digital pathology and biopsy image patches. However, learning over patch-wise features using convolutional neural networks limits the ability of the model to capture global contextual information and comprehensively model tissue composition. The phenotypical and topological distribution of constituent histological entities play a critical role in tissue diagnosis. As such, graph data representations and deep learning have attracted significant attention for encoding tissue representations, and capturing intra- and inter- entity level interactions. In this review, we provide a conceptual grounding for graph analytics in digital pathology, including entity-graph construction and graph architectures, and present their current success for tumor localization and classification, tumor invasion and staging, image retrieval, and survival prediction. We provide an overview of these methods in a systematic manner organized by the graph representation of the input image, scale, and organ on which they operate. We also outline the limitations of existing techniques, and suggest potential future research directions in this domain.

Representation learning on temporal interaction graphs (TIG) is to model complex networks with the dynamic evolution of interactions arising in a broad spectrum of problems. Existing dynamic embedding methods on TIG discretely update node embeddings merely when an interaction occurs. They fail to capture the continuous dynamic evolution of embedding trajectories of nodes. In this paper, we propose a two-module framework named ConTIG, a continuous representation method that captures the continuous dynamic evolution of node embedding trajectories. With two essential modules, our model exploit three-fold factors in dynamic networks which include latest interaction, neighbor features and inherent characteristics. In the first update module, we employ a continuous inference block to learn the nodes' state trajectories by learning from time-adjacent interaction patterns between node pairs using ordinary differential equations. In the second transform module, we introduce a self-attention mechanism to predict future node embeddings by aggregating historical temporal interaction information. Experiments results demonstrate the superiority of ConTIG on temporal link prediction, temporal node recommendation and dynamic node classification tasks compared with a range of state-of-the-art baselines, especially for long-interval interactions prediction.

Besides the typical applications of recommender systems in B2C scenarios such as movie or shopping platforms, there is a rising interest in transforming the human-driven advice provided e.g. in consultancy via the use of recommender systems. We explore the special characteristics of such knowledge-based B2B services and propose a process that allows to incorporate recommender systems into them. We suggest and compare several recommender techniques that allow to incorporate the necessary contextual knowledge (e.g. company demographics). These techniques are evaluated in isolation on a test set of business intelligence consultancy cases. We then identify the respective strengths of the different techniques and propose a new hybridisation strategy to combine these strengths. Our results show that the hybridisation leads to a substantial performance improvement over the individual methods.