Artificial intelligence (AI) enables machines to learn from human experience, adjust to new inputs, and perform human-like tasks. AI is progressing rapidly and is transforming the way businesses operate, from process automation to cognitive augmentation of tasks and intelligent process/data analytics. However, the main challenge for human users would be to understand and appropriately trust the result of AI algorithms and methods. In this paper, to address this challenge, we study and analyze the recent work done in Explainable Artificial Intelligence (XAI) methods and tools. We introduce a novel XAI process, which facilitates producing explainable models while maintaining a high level of learning performance. We present an interactive evidence-based approach to assist human users in comprehending and trusting the results and output created by AI-enabled algorithms. We adopt a typical scenario in the Banking domain for analyzing customer transactions. We develop a digital dashboard to facilitate interacting with the algorithm results and discuss how the proposed XAI method can significantly improve the confidence of data scientists in understanding the result of AI-enabled algorithms.

Most weed species can adversely impact agricultural productivity by competing for nutrients required by high-value crops. Manual weeding is not practical for large cropping areas. Many studies have been undertaken to develop automatic weed management systems for agricultural crops. In this process, one of the major tasks is to recognise the weeds from images. However, weed recognition is a challenging task. It is because weed and crop plants can be similar in colour, texture and shape which can be exacerbated further by the imaging conditions, geographic or weather conditions when the images are recorded. Advanced machine learning techniques can be used to recognise weeds from imagery. In this paper, we have investigated five state-of-the-art deep neural networks, namely VGG16, ResNet-50, Inception-V3, Inception-ResNet-v2 and MobileNetV2, and evaluated their performance for weed recognition. We have used several experimental settings and multiple dataset combinations. In particular, we constructed a large weed-crop dataset by combining several smaller datasets, mitigating class imbalance by data augmentation, and using this dataset in benchmarking the deep neural networks. We investigated the use of transfer learning techniques by preserving the pre-trained weights for extracting the features and fine-tuning them using the images of crop and weed datasets. We found that VGG16 performed better than others on small-scale datasets, while ResNet-50 performed better than other deep networks on the large combined dataset.

While knowledge graphs contain rich semantic knowledge of various entities and the relational information among them, temporal knowledge graphs (TKGs) further indicate the interactions of the entities over time. To study how to better model TKGs, automatic temporal knowledge graph completion (TKGC) has gained great interest. Recent TKGC methods aim to integrate advanced deep learning techniques, e.g., attention mechanism and Transformer, to boost model performance. However, we find that compared to adopting various kinds of complex modules, it is more beneficial to better utilize the whole amount of temporal information along the time axis. In this paper, we propose a simple but powerful graph encoder TARGCN for TKGC. TARGCN is parameter-efficient, and it extensively utilizes the information from the whole temporal context. We perform experiments on three benchmark datasets. Our model can achieve a more than 42% relative improvement on GDELT dataset compared with the state-of-the-art model. Meanwhile, it outperforms the strongest baseline on ICEWS05-15 dataset with around 18.5% fewer parameters.

As consensus across the various published AI ethics principles is approached, a gap remains between high-level principles and practical techniques that can be readily adopted to design and develop responsible AI systems. We examine the practices and experiences of researchers and engineers from Australia's national scientific research agency (CSIRO), who are involved in designing and developing AI systems for a range of purposes. Semi-structured interviews were used to examine how the practices of the participants relate to and align with a set of high-level AI ethics principles that are proposed by the Australian Government. The principles comprise: Privacy Protection & Security, Reliability & Safety, Transparency & Explainability, Fairness, Contestability, Accountability, Human-centred Values, and Human, Social & Environmental Wellbeing. The insights of the researchers and engineers as well as the challenges that arose for them in the practical application of the principles are examined. Finally, a set of organisational responses are provided to support the implementation of high-level AI ethics principles into practice.

As many fine-tuned pre-trained language models~(PLMs) with promising performance are generously released, investigating better ways to reuse these models is vital as it can greatly reduce the retraining computational cost and the potential environmental side-effects. In this paper, we explore a novel model reuse paradigm, Knowledge Amalgamation~(KA) for PLMs. Without human annotations available, KA aims to merge the knowledge from different teacher-PLMs, each of which specializes in a different classification problem, into a versatile student model. The achieve this, we design a Model Uncertainty--aware Knowledge Amalgamation~(MUKA) framework, which identifies the potential adequate teacher using Monte-Carlo Dropout for approximating the golden supervision to guide the student. Experimental results demonstrate that MUKA achieves substantial improvements over baselines on benchmark datasets. Further analysis shows that MUKA can generalize well under several complicate settings with multiple teacher models, heterogeneous teachers, and even cross-dataset teachers.

Single-Agent (SA) Reinforcement Learning systems have shown outstanding results on non-stationary problems. However, Multi-Agent Reinforcement Learning (MARL) can surpass SA systems generally and when scaling. Furthermore, MA systems can be super-powered by collaboration, which can happen through observing others, or a communication system used to share information between collaborators. Here, we developed a distributed MA learning mechanism with the ability to communicate based on decentralised partially observable Markov decision processes (Dec-POMDPs) and Graph Neural Networks (GNNs). Minimising the time and energy consumed by training Machine Learning models while improving performance can be achieved by collaborative MA mechanisms. We demonstrate this in a real-world scenario, an offshore wind farm, including a set of distributed wind turbines, where the objective is to maximise collective efficiency. Compared to a SA system, MA collaboration has shown significantly reduced training time and higher cumulative rewards in unseen and scaled scenarios.

The past two years have seen some of the biggest market disruptions for healthcare providers and organizations in living memory, which means every medical provider has a lot more information to sift through these days when it comes to picking out the best tech to invest in for their practices and patients. When you consider the surfeit of tech innovations, plus the massive additional workloads healthcare workers are dealing with due to the pandemic, it's easy to see how decision-makers in healthcare organizations can become overwhelmed. But independent practices and hospitals have to stay on the cutting edge if they want to provide the best possible care to their patients while ensuring their business also thrives. The pandemic reminded us that it's a dangerous game to try and predict with certainty what the future holds, but we can look to current healthcare trends to see what technologies may become the most widely adopted, beneficial, and necessary tools of the coming years. To that end, Gartner ran a global survey of 93 healthcare organizations with no more than 500 employees to understand their strategic planning around tech adoption (methodology below).

MLJ (Machine Learning in Julia) is a toolbox written in Julia providing a common interface and meta-algorithms for selecting, tuning, evaluating, composing and comparing over 160 machine learning models written in Julia and other languages. MLJ was initially created as a Tools, Practices and Systems project at the Alan Turing Institute in 2019. Current funding is provided by a New Zealand Strategic Science Investment Fund awarded to the University of Auckland. The functionality of MLJ is distributed over a number of repositories illustrated in the dependency chart below. These repositories live at the JuliaAI umbrella organization.

Normalizing flows have become more popular within the last few years; however, they continue to have limitations compared to other generative models, more specifically that they are computationally expensive in terms of memory and time. Early implementations of Normalizing Flows were coupling layers (Dinh et al., 2014, 2017; Kingma and Dhariwal, 2018) and autoregressive flows (Papamakarios et al., 2017; Kingma et al., 2016). These have easy to compute log-likelihoods; however, coupling layers tend to need quite a few parameters to achieve strong performance and autoregressive flows are extremely expensive to sample from. The newer technique of residual flows (Chen et al., 2019) allows for models that are built on standard components and have inductive biases that favor simpler functions (Gopal, 2020); however, these have the problem of being expensive in terms of time for computing log-likelihoods and training, as well as require quite a few layers for strong performance. Since the introduction of these models, there have been many developments that have lead to improvement in parameter efficiency such as FFJORD (Grathwohl et al., 2019), a continuous normalizing flow, that has a dynamic number of layers. However, this too can have computational problems as having a few dynamics layers can lead to hundreds of implicit layers. Among the flows introduced, the ones with provable universal approximation capability are Affine Coupling Layers (Dinh et al., 2014, 2017; Teshima et al., 2020), Neural Autoregressive Flows (NAF, Huang et al. (2018)), Block NAFs (BNAF, Cao et al. (2019)), Sum-of-Squares Polynomial Flow (Jaini et al., 2019), and Convex Potential Flows (CP-Flow, Huang et al. (2021)). Though these have been shown to be universal approximators, they do not necessarily translate into faster, more efficient training, and some of the flows listed require the expensive sampling routine of autoregressive flows.

Existing human mobility forecasting models follow the standard design of the time-series prediction model which takes a series of numerical values as input to generate a numerical value as a prediction. Although treating this as a regression problem seems straightforward, incorporating various contextual information such as the semantic category information of each Place-of-Interest (POI) is a necessary step, and often the bottleneck, in designing an effective mobility prediction model. As opposed to the typical approach, we treat forecasting as a translation problem and propose a novel forecasting through a language generation pipeline. The paper aims to address the human mobility forecasting problem as a language translation task in a sequence-to-sequence manner. A mobility-to-language template is first introduced to describe the numerical mobility data as natural language sentences. The core intuition of the human mobility forecasting translation task is to convert the input mobility description sentences into a future mobility description from which the prediction target can be obtained. Under this pipeline, a two-branch network, SHIFT (Translating Human Mobility Forecasting), is designed. Specifically, it consists of one main branch for language generation and one auxiliary branch to directly learn mobility patterns. During the training, we develop a momentum mode for better connecting and training the two branches. Extensive experiments on three real-world datasets demonstrate that the proposed SHIFT is effective and presents a new revolutionary approach to forecasting human mobility.