Researchers at UniSA have developed a cost-effective new technique to monitor soil moisture using a standard digital camera and machine learning technology. The United Nations predicts that by 2050 many areas of the planet may not have enough fresh water to meet the demands of agriculture if we continue our current patterns of use. One solution to this global dilemma is the development of more efficient irrigation, central to which is precision monitoring of soil moisture, allowing sensors to guide'smart' irrigation systems to ensure water is applied at the optimum time and rate. Current methods for sensing soil moisture are problematic – buried sensors are susceptible to salts in the substrate and require specialised hardware for connections, while thermal imaging cameras are expensive and can be compromised by climatic conditions such as sunlight intensity, fog, and clouds. Researchers from The University of South Australia and Baghdad's Middle Technical University have developed a cost-effective alternative that may make precision soil monitoring simple and affordable in almost any circumstance.

Real-world decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives. Despite this, the majority of research in reinforcement learning and decision-theoretic planning either assumes only a single objective, or that multiple objectives can be adequately handled via a simple linear combination. Such approaches may oversimplify the underlying problem and hence produce suboptimal results. This paper serves as a guide to the application of multi-objective methods to difficult problems, and is aimed at researchers who are already familiar with single-objective reinforcement learning and planning methods who wish to adopt a multi-objective perspective on their research, as well as practitioners who encounter multi-objective decision problems in practice. It identifies the factors that may influence the nature of the desired solution, and illustrates by example how these influence the design of multi-objective decision-making systems for complex problems.

A new ensemble framework for interpretable model called Linear Iterative Feature Embedding (LIFE) has been developed to achieve high prediction accuracy, easy interpretation and efficient computation simultaneously. The LIFE algorithm is able to fit a wide single-hidden-layer neural network (NN) accurately with three steps: defining the subsets of a dataset by the linear projections of neural nodes, creating the features from multiple narrow single-hidden-layer NNs trained on the different subsets of the data, combining the features with a linear model. The theoretical rationale behind LIFE is also provided by the connection to the loss ambiguity decomposition of stack ensemble methods. Both simulation and empirical experiments confirm that LIFE consistently outperforms directly trained single-hidden-layer NNs and also outperforms many other benchmark models, including multi-layers Feed Forward Neural Network (FFNN), Xgboost, and Random Forest (RF) in many experiments. As a wide single-hidden-layer NN, LIFE is intrinsically interpretable. Meanwhile, both variable importance and global main and interaction effects can be easily created and visualized. In addition, the parallel nature of the base learner building makes LIFE computationally efficient by leveraging parallel computing.

Recent works in Generative Adversarial Networks (GANs) are actively revisiting various data augmentation techniques as an effective way to prevent discriminator overfitting. It is still unclear, however, that which augmentations could actually improve GANs, and in particular, how to apply a wider range of augmentations in training. In this paper, we propose a novel way to address these questions by incorporating a recent contrastive representation learning scheme into the GAN discriminator, coined ContraD. This "fusion" enables the discriminators to work with much stronger augmentations without increasing their training instability, thereby preventing the discriminator overfitting issue in GANs more effectively. Even better, we observe that the contrastive learning itself also benefits from our GAN training, i.e., by maintaining discriminative features between real and fake samples, suggesting a strong coherence between the two worlds: good contrastive representations are also good for GAN discriminators, and vice versa. Our experimental results show that GANs with ContraD consistently improve FID and IS compared to other recent techniques incorporating data augmentations, still maintaining highly discriminative features in the discriminator in terms of the linear evaluation. Finally, as a byproduct, we also show that our GANs trained in an unsupervised manner (without labels) can induce many conditional generative models via a simple latent sampling, leveraging the learned features of ContraD. Generative adversarial networks (GANs) (Goodfellow et al., 2014) have become one of the most prominent approaches for generative modeling with a wide range of applications (Ho & Ermon, 2016; Zhu et al., 2017; Karras et al., 2019; Rott Shaham et al., 2019). In general, a GAN is defined by a minimax game between two neural networks: a generator network that maps a random vector into the data domain, and a discriminator network that classifies whether a given sample is real (from the training dataset) or fake (from the generator).

This paper proposes a new distance metric function, called Z distance, for KNN classification. The Z distance function is not a geometric direct-line distance between two data points. It gives a consideration to the class attribute of a training dataset when measuring the affinity between data points. Concretely speaking, the Z distance of two data points includes their class center distance and real distance. And its shape looks like "Z". In this way, the affinity of two data points in the same class is always stronger than that in different classes. Or, the intraclass data points are always closer than those interclass data points. We evaluated the Z distance with experiments, and demonstrated that the proposed distance function achieved better performance in KNN classification.

Multilingual models have demonstrated impressive cross-lingual transfer performance. However, test sets like XNLI are monolingual at the example level. In multilingual communities, it is common for polyglots to code-mix when conversing with each other. Inspired by this phenomenon, we present two strong black-box adversarial attacks (one word-level, one phrase-level) for multilingual models that push their ability to handle code-mixed sentences to the limit. The former uses bilingual dictionaries to propose perturbations and translations of the clean example for sense disambiguation. The latter directly aligns the clean example with its translations before extracting phrases as perturbations. Our phrase-level attack has a success rate of 89.75% against XLM-R-large, bringing its average accuracy of 79.85 down to 8.18 on XNLI. Finally, we propose an efficient adversarial training scheme that trains in the same number of steps as the original model and show that it improves model accuracy.

Building effective neural machine translation (NMT) models for very low-resourced and morphologically rich African indigenous languages is an open challenge. Besides the issue of finding available resources for them, a lot of work is put into preprocessing and tokenization. Recent studies have shown that standard tokenization methods do not always adequately deal with the grammatical, diacritical, and tonal properties of some African languages. That, coupled with the extremely low availability of training samples, hinders the production of reliable NMT models. In this paper, using Fon language as a case study, we revisit standard tokenization methods and introduce Word-Expressions-Based (WEB) tokenization, a human-involved super-words tokenization strategy to create a better representative vocabulary for training. Furthermore, we compare our tokenization strategy to others on the Fon-French and French-Fon translation tasks.

Artificial intelligence is studying more about how to utilize (and on) people. A recent research has revealed how AI can learn how to spot vulnerabilities in human customs and behaviours and use these to affect human decision-making. It might appear cliched to say AI is altering all aspects of the way we work and live, but it is true. A variety of kinds of AI are in work in areas as varied as vaccine development, environmental management and office management. And while AI doesn't have human wisdom and emotions, its abilities are strong and rapidly growing.

Adelaide (Australia): Researchers at the University of South Australia have developed a cost-effective new technique to monitor soil moisture using a standard digital camera and machine learning technology. The United Nations predicts that by 2050 many areas of the planet may not have enough fresh water to meet the demands of agriculture if we continue our current patterns of use. One solution to this global dilemma is the development of more efficient irrigation, central to which is precision monitoring of soil moisture, allowing sensors to guide'smart' irrigation systems to ensure water is applied at the optimum time and rate. Current methods for sensing soil moisture are problematic -- buried sensors are susceptible to salts in the substrate and require specialised hardware for connections, while thermal imaging cameras are expensive and can be compromised by climatic conditions such as sunlight intensity, fog, and clouds. Researchers from The University of South Australia and Baghdad's Middle Technical University have developed a cost-effective alternative that may make precision soil monitoring simple and affordable in almost any circumstance.

In news that probably won't shock you all that much, this year's Oscars reflect a year spent mostly indoors and not in movie theaters. The Academy has announced the nominees for the 2021 Oscars, and Netflix is, again, the frontrunner, grabbing 31 nominations. All those nominations won't guarantee wins, sure, but David Fincher's Mank dominated the shortlist. Its 10 nominations included Best Picture, Best Director, Best Actor (Gary Oldman) and Best Supporting Actress (Amanda Seyfried). Amazon picked up nominations for Borat: Subsequent Moviefilm, and Hulu's The United States vs. Billie Holiday was also recognized.