ImageNet-1k is a dataset often used for benchmarking machine learning (ML) models and evaluating tasks such as image recognition and object detection. Wild animals make up 27% of ImageNet-1k but, unlike classes representing people and objects, these data have not been closely scrutinized. In the current paper, we analyze the 13,450 images from 269 classes that represent wild animals in the ImageNet-1k validation set, with the participation of expert ecologists. We find that many of the classes are ill-defined or overlapping, and that 12% of the images are incorrectly labeled, with some classes having >90% of images incorrect. We also find that both the wildlife-related labels and images included in ImageNet-1k present significant geographical and cultural biases, as well as ambiguities such as artificial animals, multiple species in the same image, or the presence of humans. Our findings highlight serious issues with the extensive use of this dataset for evaluating ML systems, the use of such algorithms in wildlife-related tasks, and more broadly the ways in which ML datasets are commonly created and curated.

Machine learning (ML) methods can effectively analyse data, recognize patterns in them, and make high-quality predictions. Good predictions usually come along with "black-box" models that are unable to present the detected patterns in a human-readable way. Technical developments recently led to eXplainable Artificial Intelligence (XAI) techniques that aim to open such black-boxes and enable humans to gain new insights from detected patterns. We investigated the application of XAI in an area where specific insights can have a significant effect on consumer behaviour, namely electricity use. Knowing that specific feedback on individuals' electricity consumption triggers resource conservation, we created five visualizations with ML and XAI methods from electricity consumption time series for highly personalized feedback, considering existing domain-specific design knowledge. Our experimental evaluation with 152 participants showed that humans can assimilate the pattern displayed by XAI visualizations, but such visualizations should follow known visualization patterns to be well-understood by users.

The wide spread of false information online including misinformation and disinformation has become a major problem for our highly digitised and globalised society. A lot of research has been done to better understand different aspects of false information online such as behaviours of different actors and patterns of spreading, and also on better detection and prevention of such information using technical and socio-technical means. One major approach to detect and debunk false information online is to use human fact-checkers, who can be helped by automated tools. Despite a lot of research done, we noticed a significant gap on the lack of conceptual models describing the complicated ecosystems of false information and fact checking. In this paper, we report the first graphical models of such ecosystems, focusing on false information online in multiple contexts, including traditional media outlets and user-generated content. The proposed models cover a wide range of entity types and relationships, and can be a new useful tool for researchers and practitioners to study false information online and the effects of fact checking.

In this paper, we propose our information-theoretic equivalence of entropic multi-marginal optimal transport (MOT). This equivalence can be easily reduced to the case of entropic optimal transport (OT). Because OT is widely used to compare differences between knowledge or beliefs, we apply this result to the communication between agents with different beliefs. Our results formally prove the statement that entropic OT is information-theoretically optimal given by Wang et al. [2020] and generalize it to the multi-agent case. We believe that our work can shed light on OT theory in future multi-agent teaming systems.

Person re-identification (re-ID) via 3D skeletons is an important emerging topic with many merits. Existing solutions rarely explore valuable body-component relations in skeletal structure or motion, and they typically lack the ability to learn general representations with unlabeled skeleton data for person re-ID. This paper proposes a generic unsupervised Skeleton Prototype Contrastive learning paradigm with Multi-level Graph Relation learning (SPC-MGR) to learn effective representations from unlabeled skeletons to perform person re-ID. Specifically, we first construct unified multi-level skeleton graphs to fully model body structure within skeletons. Then we propose a multi-head structural relation layer to comprehensively capture relations of physically-connected body-component nodes in graphs. A full-level collaborative relation layer is exploited to infer collaboration between motion-related body parts at various levels, so as to capture rich body features and recognizable walking patterns. Lastly, we propose a skeleton prototype contrastive learning scheme that clusters feature-correlative instances of unlabeled graph representations and contrasts their inherent similarity with representative skeleton features ("skeleton prototypes") to learn discriminative skeleton representations for person re-ID. Empirical evaluations show that SPC-MGR significantly outperforms several state-of-the-art skeleton-based methods, and it also achieves highly competitive person re-ID performance for more general scenarios.

Edtech startup Mindjoy reached more than 1 200 children between the ages of 11 and 15 during the July and August winter breaks with its artificial intelligence (AI) hackathons. Hackathons were hosted by 14 schools in KwaZulu-Natal, Gauteng and the Western Cape, as well as virtually for children in Kenya and the Netherlands. Plans are in place to reach a further 10 schools by the end of September, in an effort to help learners come to grips with the Fourth Industrial Revolution (4IR) and what AI means for their future. Mindjoy's hackathons immerse students in a world of code and allow them to learn with some of the most advanced AI technology in the world – GPT-3 created by OpenAI. Students are given "kid-shaped" problems – such as doing their homework – to solve, and a technology to use to build solutions to the problems.

Incorrectly sized balloon catheters can lead to increased post-surgical complications, yet even with preoperative imaging, correct selection remains a challenge. With limited feedback during surgery, it is difficult to verify correct deployment. We propose the use of integrated impedance measurements and Electrical Impedance Tomography (EIT) imaging to assess the deformation of the balloon and determine the size and shape of the surrounding lumen. Previous work using single impedance measurements, or pressure data and analytical models, whilst demonstrating high sizing accuracy, have assumed a circular cross section. Here we extend these methods by adding a multitude of electrodes to detect elliptical and occluded lumen and obtain EIT images to localise deformations. Using a 14 Fr (5.3 mm) catheter as an example, numerical simulations were performed to find the optimal electrode configuration of two rings of 8 electrodes spaced 10 mm apart. The simulations predicted that the maximum detectable aspect ratio decreased from 0.9 for a 14mm balloon to 0.5 at 30mm. The sizing and ellipticity detection results were verified experimentally. A prototype robotic balloon catheter was constructed to automatically inflate a compliant balloon while simultaneously recording EIT and pressure data. Data were collected in experiments replicating stenotic vessels with an elliptical and asymmetrical profile, and the widening of a lumen during angioplasty. After calibration, the system was able to correctly localise the occlusion and detect aspect ratios of 0.75. EIT images further localised the occlusion and visualised the dilation of the lumen during balloon inflation.

Commonsense reasoning is an appealing topic in natural language processing (NLP) as it plays a fundamental role in supporting the human-like actions of NLP systems. With large-scale language models as the backbone, unsupervised pre-training on numerous corpora shows the potential to capture commonsense knowledge. Current pre-trained language model (PLM)-based reasoning follows the traditional practice using perplexity metric. However, commonsense reasoning is more than existing probability evaluation, which is biased by word frequency. This paper reconsiders the nature of commonsense reasoning and proposes a novel commonsense reasoning metric, Non-Replacement Confidence (NRC). In detail, it works on PLMs according to the Replaced Token Detection (RTD) pre-training objective in ELECTRA, in which the corruption detection objective reflects the confidence on contextual integrity that is more relevant to commonsense reasoning than existing probability. Our proposed novel method boosts zero-shot performance on two commonsense reasoning benchmark datasets and further seven commonsense question-answering datasets. Our analysis shows that pre-endowed commonsense knowledge, especially for RTD-based PLMs, is essential in downstream reasoning.

Semantic search for candidate retrieval is an important yet neglected problem in retrieval-based Chatbots, which aims to select a bunch of candidate responses efficiently from a large pool. The existing bottleneck is to ensure the model architecture having two points: 1) rich interactions between a query and a response to produce query-relevant responses; 2) ability of separately projecting the query and the response into latent spaces to apply efficiently in semantic search during online inference. To tackle this problem, we propose a novel approach, called Multitask-based Semantic Search Neural Network (MSSNN) for candidate retrieval, which accomplishes query-response interactions through multi-tasks. The method employs a Seq2Seq modeling task to learn a good query encoder, and then performs a word prediction task to build response embeddings, finally conducts a simple matching model to form the dot-product scorer. Experimental studies have demonstrated the potential of the proposed approach.

Representing deep neural networks (DNNs) in low-precision is a promising approach to enable efficient acceleration and memory reduction. Previous methods that train DNNs in low-precision typically keep a copy of weights in high-precision during the weight updates. Directly training with low-precision weights leads to accuracy degradation due to complex interactions between the low-precision number systems and the learning algorithms. To address this issue, we develop a co-designed low-precision training framework, termed LNS-Madam, in which we jointly design a logarithmic number system (LNS) and a multiplicative weight update algorithm (Madam). We prove that LNS-Madam results in low quantization error during weight updates, leading to stable performance even if the precision is limited. We further propose a hardware design of LNS-Madam that resolves practical challenges in implementing an efficient datapath for LNS computations. Our implementation effectively reduces energy overhead incurred by LNS-to-integer conversion and partial sum accumulation. Experimental results show that LNS-Madam achieves comparable accuracy to full-precision counterparts with only 8 bits on popular computer vision and natural language tasks. Compared to FP32 and FP8, LNS-Madam reduces the energy consumption by over 90% and 55%, respectively.