Conventional saliency maps highlight input features to which neural network predictions are highly sensitive. We take a different approach to saliency, in which we identify and analyze the network parameters, rather than inputs, which are responsible for erroneous decisions. We first verify that identified salient parameters are indeed responsible for misclassification by showing that turning these parameters off improves predictions on the associated samples, more than turning off the same number of random or least salient parameters. We further validate the link between salient parameters and network misclassification errors by observing that fine-tuning a small number of the most salient parameters on a single sample results in error correction on other samples which were misclassified for similar reasons - nearest neighbors in the saliency space. After validating our parameter-space saliency maps, we demonstrate that samples which cause similar parameters to malfunction are semantically similar. Further, we introduce an input-space saliency counterpart which reveals how image features cause specific network components to malfunction.

Criminals have become increasingly experienced in using cryptocurrencies, such as Bitcoin, for money laundering. The use of cryptocurrencies can hide criminal identities and transfer hundreds of millions of dollars of dirty funds through their criminal digital wallets. However, this is considered a paradox because cryptocurrencies are goldmines for open-source intelligence, giving law enforcement agencies more power when conducting forensic analyses. This paper proposed Inspection-L, a graph neural network (GNN) framework based on a self-supervised Deep Graph Infomax (DGI) and Graph Isomorphism Network (GIN), with supervised learning algorithms, namely Random Forest (RF), to detect illicit transactions for anti-money laundering (AML). To the best of our knowledge, our proposal is the first to apply self-supervised GNNs to the problem of AML in Bitcoin. The proposed method was evaluated on the Elliptic dataset and shows that our approach outperforms the state-of-the-art in terms of key classification metrics, which demonstrates the potential of self-supervised GNN in the detection of illicit cryptocurrency transactions.

A new chatbot start-up from two top artificial intelligence talents lets anyone strike up a conversation with impersonations of Donald Trump, Elon Musk, Albert Einstein and Sherlock Holmes. Registered users type in messages and get responses. They can also create a chatbot of their own on Character.ai, "There were reports of possible voter fraud and I wanted an investigation," the Trump bot said. The start-up's two founders helped create Google's artificial intelligence project LaMDA, which Google keeps closely guarded while it develops safeguards against social risks.

Dublin has long been home to Big Tech's European outposts, drawn by low taxes and Ireland's position as the only English-speaking country in the European Union. Historically, however, this has negatively affected local startups: Big salaries and cushy positions at Big Tech companies made it difficult for smaller, nimbler companies to compete. That situation is finally changing: "Over the past few years, the culture has shifted away from Big Tech," says Nicola McClafferty, chair of the Irish Venture Capital Association and a partner in Molten Ventures, a venture capital firm operating in Ireland. "We're seeing more and more people and talent wanting to come out of those companies, and really thinking about joining earlier-stage and high-growth startups." That's in part down to Irish startup successes like communications platform Intercom and payments system Stripe, which have proven homegrown wins are possible.

An artificial intelligence-powered digital health worker has been unveiled by the World Health Organisation (WHO) as its latest tool for disseminating reliable health information to the public. Originally developed by New Zealand tech company Soul Machines, with support of the Qatar Ministry of Health, the first version of the virtual health worker was used to combat misinformation about the pandemic. The new version – dubbed Florence 2.0 – covers a broader range of topics. Along with advice on COVID-19 vaccines and treatments, it can also share advice on mental health, give tips to de-stress, provide guidance on how to eat healthily and be more active, and quit tobacco and e-cigarettes, according to the WHO. The chatbot can currently converse in English, with Arabic, French, Spanish, Chinese, Hindi, and Russian to follow.

For two decades, the formalism of quantum mechanics has been successfully used to describe human decision processes, situations of heuristic reasoning, and the contextuality of concepts and their combinations. The phenomenon of 'categorical perception' has put us on track to find a possible deeper cause of the presence of this quantum structure in human cognition. Thus, we show that in an archetype of human perception consisting of the reconciliation of a bottom up stimulus with a top down cognitive expectation pattern, there arises the typical warping of categorical perception, where groups of stimuli clump together to form quanta, which move away from each other and lead to a discretization of a dimension. The individual concepts, which are these quanta, can be modeled by a quantum prototype theory with the square of the absolute value of a corresponding Schr\"odinger wave function as the fuzzy prototype structure, and the superposition of two such wave functions accounts for the interference pattern that occurs when these concepts are combined. Using a simple quantum measurement model, we analyze this archetype of human perception, provide an overview of the experimental evidence base for categorical perception with the phenomenon of warping leading to quantization, and illustrate our analyses with two examples worked out in detail.

In this paper, we investigate signal detection in multiple-input-multiple-output (MIMO) communication systems with hardware impairments, such as power amplifier nonlinearity and in-phase/quadrature imbalance. To deal with the complex combined effects of hardware imperfections, neural network (NN) techniques, in particular deep neural networks (DNNs), have been studied to directly compensate for the impact of hardware impairments. However, it is difficult to train a DNN with limited pilot signals, hindering its practical applications. In this work, we investigate how to achieve efficient Bayesian signal detection in MIMO systems with hardware imperfections. Characterizing combined hardware imperfections often leads to complicated signal models, making Bayesian signal detection challenging. To address this issue, we first train an NN to "model" the MIMO system with hardware imperfections and then perform Bayesian inference based on the trained NN. Modelling the MIMO system with NN enables the design of NN architectures based on the signal flow of the MIMO system, minimizing the number of NN layers and parameters, which is crucial to achieving efficient training with limited pilot signals. We then represent the trained NN with a factor graph, and design an efficient message passing based Bayesian signal detector, leveraging the unitary approximate message passing (UAMP) algorithm. The implementation of a turbo receiver with the proposed Bayesian detector is also investigated. Extensive simulation results demonstrate that the proposed technique delivers remarkably better performance than state-of-the-art methods.

We present a Chinese BERT model dubbed MarkBERT that uses word information in this work. Existing word-based BERT models regard words as basic units, however, due to the vocabulary limit of BERT, they only cover high-frequency words and fall back to character level when encountering out-of-vocabulary (OOV) words. Different from existing works, MarkBERT keeps the vocabulary being Chinese characters and inserts boundary markers between contiguous words. Such design enables the model to handle any words in the same way, no matter they are OOV words or not. Besides, our model has two additional benefits: first, it is convenient to add word-level learning objectives over markers, which is complementary to traditional character and sentence-level pretraining tasks; second, it can easily incorporate richer semantics such as POS tags of words by replacing generic markers with POS tag-specific markers. With the simple markers insertion, MarkBERT can improve the performances of various downstream tasks including language understanding and sequence labeling. \footnote{All the codes and models will be made publicly available at \url{https://github.com/daiyongya/markbert}}

In the fight against wildlife trafficking, Australian scientists are using the power of artificial intelligence. The method detects animals being smuggled in luggage or the mail using 3-Dimensional X-rays at airports and post offices, and algorithms then warn customs agents. This device uses artificial intelligence to recognize the morphologies of animals that are being trafficked. Australia has a diverse flora and fauna, which has supported an illicit wildlife trade. The researchers created a 3D-scanned "reference library" for three types of wildlife: lizards, birds, and fish, which they used to teach artificial intelligence algorithms to recognize the species.

The loss of any life can be devastating, but the loss of a life from suicide is especially tragic. Around nine Australians take their own life each day, and it is the leading cause of death for Australians aged 15–44. Suicide attempts are more common, with some estimates stating that they occur up to 30 times as often as deaths. "Suicide has large effects when it happens. It impacts many people and has far-reaching consequences for family, friends and communities," says Karen Kusuma, a UNSW Sydney PhD candidate in psychiatry at the Black Dog Institute, who investigates suicide prevention in adolescents.