In this paper, we propose SCANING, an unsupervised framework for paraphrasing via controlled noise injection. We focus on the novel task of paraphrasing algebraic word problems having practical applications in online pedagogy as a means to reduce plagiarism as well as ensure understanding on the part of the student instead of rote memorization. This task is more complex than paraphrasing general-domain corpora due to the difficulty in preserving critical information for solution consistency of the paraphrased word problem, managing the increased length of the text and ensuring diversity in the generated paraphrase. Existing approaches fail to demonstrate adequate performance on at least one, if not all, of these facets, necessitating the need for a more comprehensive solution. To this end, we model the noising search space as a composition of contextual and syntactic aspects and sample noising functions consisting of either one or both aspects. This allows for learning a denoising function that operates over both aspects and produces semantically equivalent and syntactically diverse outputs through grounded noise injection. The denoising function serves as a foundation for learning a paraphrasing function which operates solely in the input-paraphrase space without carrying any direct dependency on noise. We demonstrate SCANING considerably improves performance in terms of both semantic preservation and producing diverse paraphrases through extensive automated and manual evaluation across 4 datasets.

Interactions with articulated objects are a challenging but important task for mobile robots. To tackle this challenge, we propose a novel closed-loop control pipeline, which integrates manipulation priors from affordance estimation with sampling-based whole-body control. We introduce the concept of agent-aware affordances which fully reflect the agent's capabilities and embodiment and we show that they outperform their state-of-the-art counterparts which are only conditioned on the end-effector geometry. Additionally, closed-loop affordance inference is found to allow the agent to divide a task into multiple non-continuous motions and recover from failure and unexpected states. Finally, the pipeline is able to perform long-horizon mobile manipulation tasks, i.e. opening and closing an oven, in the real world with high success rates (opening: 71%, closing: 72%).

Uncertainty quantification of machine learning and deep learning methods plays an important role in enhancing trust to the obtained result. In recent years, a numerous number of uncertainty quantification methods have been introduced. Monte Carlo dropout (MC-Dropout) is one of the most well-known techniques to quantify uncertainty in deep learning methods. In this study, we propose two new loss functions by combining cross entropy with Expected Calibration Error (ECE) and Predictive Entropy (PE). The obtained results clearly show that the new proposed loss functions lead to having a calibrated MC-Dropout method. Our results confirmed the great impact of the new hybrid loss functions for minimising the overlap between the distributions of uncertainty estimates for correct and incorrect predictions without sacrificing the model's overall performance.

The effectiveness of machine learning models is significantly affected by the size of the dataset and the quality of features as redundant and irrelevant features can radically degrade the performance. This paper proposes IGRF-RFE: a hybrid feature selection method tasked for multi-class network anomalies using a Multilayer perceptron (MLP) network. IGRF-RFE can be considered as a feature reduction technique based on both the filter feature selection method and the wrapper feature selection method. In our proposed method, we use the filter feature selection method, which is the combination of Information Gain and Random Forest Importance, to reduce the feature subset search space. Then, we apply recursive feature elimination(RFE) as a wrapper feature selection method to further eliminate redundant features recursively on the reduced feature subsets. Our experimental results obtained based on the UNSW-NB15 dataset confirm that our proposed method can improve the accuracy of anomaly detection while reducing the feature dimension. The results show that the feature dimension is reduced from 42 to 23 while the multi-classification accuracy of MLP is improved from 82.25% to 84.24%.

Recently, Graph Neural Networks (GNNs) achieve remarkable success in Recommendation. To reduce the influence of data sparsity, Graph Contrastive Learning (GCL) is adopted in GNN-based CF methods for enhancing performance. Most GCL methods consist of data augmentation and contrastive loss (e.g., InfoNCE). GCL methods construct the contrastive pairs by hand-crafted graph augmentations and maximize the agreement between different views of the same node compared to that of other nodes, which is known as the InfoMax principle. However, improper data augmentation will hinder the performance of GCL. InfoMin principle, that the good set of views shares minimal information and gives guidelines to design better data augmentation. In this paper, we first propose a new data augmentation (i.e., edge-operating including edge-adding and edge-dropping). Then, guided by InfoMin principle, we propose a novel theoretical guiding contrastive learning framework, named Learnable Data Augmentation for Graph Contrastive Learning (LDA-GCL). Our methods include data augmentation learning and graph contrastive learning, which follow the InfoMin and InfoMax principles, respectively. In implementation, our methods optimize the adversarial loss function to learn data augmentation and effective representations of users and items. Extensive experiments on four public benchmark datasets demonstrate the effectiveness of LDA-GCL.

The problem of computing minimally sparse solutions of under-determined linear systems is $NP$ hard in general. Subsets with extra properties, may allow efficient algorithms, most notably problems with the restricted isometry property (RIP) can be solved by convex $\ell_1$-minimization. While these classes have been very successful, they leave out many practical applications. In this paper, we consider adaptable classes that are tractable after training on a curriculum of increasingly difficult samples. The setup is intended as a candidate model for a human mathematician, who may not be able to tackle an arbitrary proof right away, but may be successful in relatively flexible subclasses, or areas of expertise, after training on a suitable curriculum.

This paper proposes a new variable stiffness soft gripper that enables high-performance grasping tasks in industrial applications. The design of the proposed monolithic soft gripper includes a middle bellow and two side bellows (i.e., fingers). The positions of the fingers are regulated by adjusting the negative pressure in the middle bellow actuator via an on-off controller. The stiffness of the soft gripper is modulated by controlling the positive pressure in the fingers through the use of a proportional air-pressure regulator. It is experimentally shown that the proposed soft gripper can modulate its stiffness by 125% within 250ms. It is also shown that the variable stiffness soft gripper can help improve the safety and performance of grasping tasks in industrial applications.

Officials had to close Mullaloo Beach in Perth, Western Australia, for the second time in a week on Monday, January 9, after a tiger shark was spotted swimming close to the shore. Check out this video, taken from a drone. A 16-year-old girl died after a shark mauled her while swimming in the Swan River in Australia, with only a teen diving in to save her as others watched in horror. "A female received injuries after being bitten by an unknown species of shark at approximately 3.35pm on Feb. 4 2023," the Department of Primary Industries and Regional Development (DPIRD) said of the incident. "DPIRD is working with WA Police and local authorities to coordinate responses. A DPIRD Fisheries vessel is on the water monitoring the area, and DPIRD officers are conducting land-based patrols."

According to the White House, the informal Quad alliance of Australia, India, Japan, and the United States has decided to deploy machine learning and other cutting-edge technology to improve cyber security. During a meeting of the Quad Senior Cyber Group on January 30 and 31, representatives from Australia, India, Japan, and the United States reaffirmed their commitment to advancing an inclusive, free, and open Indo-Pacific region, according to the statement. The Group pledged to use machine learning and related cutting-edge technologies in the long run to improve cyber security and create secure channels for private sector threat information sharing and Computer Emergency Response Teams (CERT), according to a statement released by the White House on Thursday. It added that these goals are a key component of the group's forward-thinking, cutting-edge work plan. The group also committed to developing a framework and methodology for ensuring supply chain security and resilience for information communication technologies (ICT) and operational technology (OT) systems of critical sectors.

This summer, a coding class offered by a private school in Austin, Texas, was led by an unusual teacher. The PreK-8 school, Paragon Prep, offered a series of optional, self-paced, video lessons that were automatically generated from a textbook. In them, an animated avatar made to look like the 19th-century computing pioneer Ada Lovelace taught the basics of the Python programming language. "We'll also look at basic concepts of data analysis, using NumPy as well as Pandas," said the avatar in a female computer voice that sounds more like the iPhone's Siri than like a 19th-century British mathematician, her mouth moving clumsily as she speaks. "If you have no idea what any of that means, that's perfectly fine, good and normal. This course was meant for anyone interested in becoming a future software engineer or data scientist, not someone who is already one."