To combat the recent coronavirus disease 2019 (COVID-19), academician and clinician are in search of new approaches to predict the COVID-19 outbreak dynamic trends that may slow down or stop the pandemic. But these epidemiological models based on mathematical assumptions may not predict the real pandemic situation. Recently the new machine learning approaches are being used to understand the dynamic trend of COVID-19 spread. In this paper, we designed the recurrent and convolutional neural network models: vanilla LSTM, stacked LSTM, ED-LSTM, Bi-LSTM, CNN, and hybrid CNN LSTM model to capture the complex trend of COVID-19 outbreak and perform the forecasting of COVID-19 daily confirmed cases of 7, 14, 21 days for India and its four most affected states (Maharashtra, Kerala, Karnataka, and Tamil Nadu). The root mean square error (RMSE) and mean absolute percentage error (MAPE) evaluation metric are computed on the testing data to demonstrate the relative performance of these models. The results show that the stacked LSTM and hybrid CNN LSTM models perform best relative to other models.

Self-supervised learning is the learning method for Deep Learning models that tries to capture meaningful features without the supervision of humans that force the model to map input data to specific labels. There are several self-supervised learning methods that are mentioned in 10L -- Self-supervised learning in computer vision. In this article, I share one method that I made (as far as I know). The proposed method uses the vector sum logic that is told in the Future Research Section of VeriMedi: Pill Identification using Proxybased Deep Metric Learning and Exact Solution. For calculating the loss, I used Euler's number because of its graph.

Data visualization is the graphical representation of information and data. Our eyes are drawn to colors to patterns. When we see a chart or a plot we can quickly understand the trends or identify the outliers. In any machine learning or deep learning task, cleaning or pre-processing the data is as important as model building. And when it comes to unstructured data like text, this process is even more important.

More and more evidence has demonstrated that graph representation learning especially graph neural networks (GNNs) has tremendously facilitated computational tasks on graphs including both node-focused and graph-focused tasks. The revolutionary advances brought by GNNs have also immensely contributed to the depth and breadth of the adoption of graph representation learning in real-world applications. For the classical application domains of graph representation learning such as recommender systems and social network analysis, GNNs result in state-of-the-art performance and bring them into new frontiers. Meanwhile, new application domains of GNNs have been continuously emerging such as combinational optimization, physics, and healthcare. These wide applications of GNNs enable diverse contributions and perspectives from disparate disciplines and make this research field truly interdisciplinary.

Machine learning studies algorithms and statistical models that computers use to perform tasks without explicit instructions [1]. The origin behind these technological advances can be largely traced back to a series of breakthroughs in artificial intelligence, in particular those based on deep learning, where data are processed through the sequential combination of multiple nonlinear layers [3]. Deep learning has accelerated the adoption of artificial intelligence with notable advances in areas ranging from computer vision [4] and natural language processing [5], to scientific applications such as drug discovery [6] and protein folding [7]. Recently, the condensed matter physics, quantum information, statistical physics, and atomic, molecular, and optical physics communities have turned their attention to the algorithms underlying modern machine learning with the objective of making progress in quantum matter research. This recent resurgence of research interest at the intersection between strongly correlated systems and machine learning is shaped in part by the commonalities in the structure of the problems that these seemingly unrelated fields attack.

Reproduced under a CC BY 4.0 license. Here are the most tweeted papers that were uploaded onto arXiv during August 2021. Results are powered by Arxiv Sanity Preserver. How to avoid machine learning pitfalls: a guide for academic researchers Michael A. Lones Submitted to arXiv on: 5 August 2021 Abstract: This document gives a concise outline of some of the common mistakes that occur when using machine learning techniques, and what can be done to avoid them. It is intended primarily as a guide for research students, and focuses on issues that are of particular concern within academic research, such as the need to do rigorous comparisons and reach valid conclusions.

Building the best model is a key step after exploratory data analysis and feature selection in any data science project. In deep learning this process consists of building layers by layers complexes neural networks (Perceptron, Vanilla, Convolutives, Recurrent) that will fit the data. In most cases, the data need to be processed from images, voices, videos, text, and numbers into matrix formats. Finding innovative ways to obtain the best model and prediction in few lines of code is a tremendous advantage especially when classifying images for computer vision applications. Automate model selection methods for deep learning of images datasets generally include Autokeras and Azure studio.

The top-k recommendation is a fundamental task in recommendation systems which is generally learned by comparing positive and negative pairs. The Contrastive Loss (CL) is the key in contrastive learning that has received more attention recently and we find it is well suited for top-k recommendations. However, it is a problem that CL treats the importance of the positive and negative samples as the same. On the one hand, CL faces the imbalance problem of one positive sample and many negative samples. On the other hand, positive items are so few in sparser datasets that their importance should be emphasized. Moreover, the other important issue is that the sparse positive items are still not sufficiently utilized in recommendations. So we propose a new data augmentation method by using multiple positive items (or samples) simultaneously with the CL loss function. Therefore, we propose a Multi-Sample based Contrastive Loss (MSCL) function which solves the two problems by balancing the importance of positive and negative samples and data augmentation. And based on the graph convolution network (GCN) method, experimental results demonstrate the state-of-the-art performance of MSCL. The proposed MSCL is simple and can be applied in many methods. We will release our code on GitHub upon the acceptance.

Autonomous driving is the key technology of intelligent logistics in Industrial Internet of Things (IIoT). In autonomous driving, the appearance of incomplete point clouds losing geometric and semantic information is inevitable owing to limitations of occlusion, sensor resolution, and viewing angle when the Light Detection And Ranging (LiDAR) is applied. The emergence of incomplete point clouds, especially incomplete vehicle point clouds, would lead to the reduction of the accuracy of autonomous driving vehicles in object detection, traffic alert, and collision avoidance. Existing point cloud completion networks, such as Point Fractal Network (PF-Net), focus on the accuracy of point cloud completion, without considering the efficiency of inference process, which makes it difficult for them to be deployed for vehicle point cloud repair in autonomous driving. To address the above problem, in this paper, we propose an efficient deep learning approach to repair incomplete vehicle point cloud accurately and efficiently in autonomous driving. In the proposed method, an efficient downsampling algorithm combining incremental sampling and one-time sampling is presented to improves the inference speed of the PF-Net based on Generative Adversarial Network (GAN). To evaluate the performance of the proposed method, a real dataset is used, and an autonomous driving scene is created, where three incomplete vehicle point clouds with 5 different sizes are set for three autonomous driving situations. The improved PF-Net can achieve the speedups of over 19x with almost the same accuracy when compared to the original PF-Net. Experimental results demonstrate that the improved PF-Net can be applied to efficiently complete vehicle point clouds in autonomous driving.

The broad scope of obstacle avoidance has led to many kinds of computer vision-based approaches. Despite its popularity, it is not a solved problem. Traditional computer vision techniques using cameras and depth sensors often focus on static scenes, or rely on priors about the obstacles. Recent developments in bio-inspired sensors present event cameras as a compelling choice for dynamic scenes. Although these sensors have many advantages over their frame-based counterparts, such as high dynamic range and temporal resolution, event-based perception has largely remained in 2D. This often leads to solutions reliant on heuristics and specific to a particular task. We show that the fusion of events and depth overcomes the failure cases of each individual modality when performing obstacle avoidance. Our proposed approach unifies event camera and lidar streams to estimate metric time-to-impact without prior knowledge of the scene geometry or obstacles. In addition, we release an extensive event-based dataset with six visual streams spanning over 700 scanned scenes.