For data isolated islands and privacy issues, federated learning has been extensively invoking much interest since it allows clients to collaborate on training a global model using their local data without sharing any with a third party. However, the existing federated learning frameworks always need sophisticated condition configurations (e.g., sophisticated driver configuration of standalone graphics card like NVIDIA, compile environment) that bring much inconvenience for large-scale development and deployment. To facilitate the deployment of federated learning and the implementation of related applications, we innovatively propose WebFed, a novel browser-based federated learning framework that takes advantage of the browser's features (e.g., Cross-platform, JavaScript Programming Features) and enhances the privacy protection via local differential privacy mechanism. Finally, We conduct experiments on heterogeneous devices to evaluate the performance of the proposed WebFed framework.

The paper utilizes the graph embeddings generated for entities of a large biomedical database to perform link prediction to capture various new relationships among different entities. A novel node similarity measure is proposed that utilizes the graph embeddings and link prediction scores to find similarity scores among various drugs which can be used by the medical experts to recommend alternative drugs to avoid side effects from original one. Utilizing machine learning on knowledge graph for drug similarity and recommendation will be less costly and less time consuming with higher scalability as compared to traditional biomedical methods due to the dependency on costly medical equipment and experts of the latter ones.

In the United States, hurricanes are the most devastating natural disasters causing billions of dollars worth of damage every year. More importantly, construction jobsites are classified among the most vulnerable environments to severe wind events. During hurricanes, unsecured and incomplete elements of construction sites, such as scaffoldings, plywoods, and metal rods, will become the potential wind-borne debris, causing cascading damages to the construction projects and the neighboring communities. Thus, it is no wonder that construction firms implement jobsite emergency plans to enforce preparedness responses before extreme weather events. However, relying on checklist-based emergency action plans to carry out a thorough hurricane preparedness is challenging in large-scale and complex site environments. For enabling systematic responses for hurricane preparedness, we have proposed a vision-based technique to identify and analyze the potential wind-borne debris in construction jobsites. Building on this, this paper demonstrates the fidelity of a new machine vision-based method to support construction site hurricane preparedness and further discuss its implications. The outcomes indicate that the convenience of visual data collection and the advantages of the machine vision-based frameworks enable rapid scene understanding and thus, provide critical heads up for practitioners to recognize and localize the potential wind-borne derbies in construction jobsites and effectively implement hurricane preparedness.

Convolutional Neural Networks (CNNs) have been widely applied. But as the CNNs grow, the number of arithmetic operations and memory footprint also increase. Furthermore, typical non-linear activation functions do not allow associativity of the operations encoded by consecutive layers, preventing the simplification of intermediate steps by combining them. We present a new activation function that allows associativity between sequential layers of CNNs. Even though our activation function is non-linear, it can be represented by a sequence of linear operations in the conformal model for Euclidean geometry. In this domain, operations like, but not limited to, convolution, average pooling, and dropout remain linear. We take advantage of associativity to combine all the "conformal layers" and make the cost of inference constant regardless of the depth of the network.

Vision transformers (ViTs) have pushed the state-of-the-art for various visual recognition tasks by patch-wise image tokenization followed by self-attention. However, the employment of self-attention modules results in a quadratic complexity in both computation and memory usage. Various attempts on approximating the self-attention computation with linear complexity have been made in Natural Language Processing. However, an in-depth analysis in this work shows that they are either theoretically flawed or empirically ineffective for visual recognition. We further identify that their limitations are rooted in keeping the softmax self-attention during approximations. Specifically, conventional self-attention is computed by normalizing the scaled dot-product between token feature vectors. Keeping this softmax operation challenges any subsequent linearization efforts. Based on this insight, for the first time, a softmax-free transformer or SOFT is proposed. To remove softmax in self-attention, Gaussian kernel function is used to replace the dot-product similarity without further normalization. This enables a full self-attention matrix to be approximated via a low-rank matrix decomposition. The robustness of the approximation is achieved by calculating its Moore-Penrose inverse using a Newton-Raphson method. Extensive experiments on ImageNet show that our SOFT significantly improves the computational efficiency of existing ViT variants. Crucially, with a linear complexity, much longer token sequences are permitted in SOFT, resulting in superior trade-off between accuracy and complexity.

Neuronal representations within artificial neural networks are commonly understood as logits, representing the log-odds score of presence (versus absence) of features within the stimulus. Under this interpretation, we can derive the probability $P(x_0 \land x_1)$ that a pair of independent features are both present in the stimulus from their logits. By converting the resulting probability back into a logit, we obtain a logit-space equivalent of the AND operation. However, since this function involves taking multiple exponents and logarithms, it is not well suited to be directly used within neural networks. We thus constructed an efficient approximation named $\text{AND}_\text{AIL}$ (the AND operator Approximate for Independent Logits) utilizing only comparison and addition operations, which can be deployed as an activation function in neural networks. Like MaxOut, $\text{AND}_\text{AIL}$ is a generalization of ReLU to two-dimensions. Additionally, we constructed efficient approximations of the logit-space equivalents to the OR and XNOR operators. We deployed these new activation functions, both in isolation and in conjunction, and demonstrated their effectiveness on a variety of tasks including image classification, transfer learning, abstract reasoning, and compositional zero-shot learning.

Currently, the development of computer games has shown a tremendous surge. The ease and speed of internet access today have also influenced the development of computer games, especially computer games that are played online. Internet technology has allowed computer games to be played in multiplayer mode. Interaction between players in a computer game can be built in several ways, one of which is by providing balanced opponents. Opponents can be developed using intelligent agents. On the other hand, research on developing intelligent agents is also growing rapidly. In computer game development, one of the easiest ways to measure the performance of an intelligent agent is to develop a virtual environment that allows the intelligent agent to interact with other players. In this research, we try to develop an intelligent agent and virtual environment for the board game. To be easily accessible, the intelligent agent and virtual environment are then developed into an Application Programming Interface (API) service called Gapoera API. The Gapoera API service that is built is expected to help game developers develop a game without having to think much about the artificial intelligence that will be embedded in the game. This service provides a basic multilevel intelligent agent that can provide users with playing board games commonly played in Indonesia. Although the Gapoera API can be used for various types of games, in this paper, we will focus on the discussion on a popular traditional board game in Indonesia, namely Mancala. The test results conclude that the multilevel agent concept developed has worked as expected. On the other hand, the development of the Gapoera API service has also been successfully accessed on several game platforms.

In the past ten years artificial intelligence has encountered such dramatic progress that it is seen now as a tool of choice to solve environmental issues and in the first place greenhouse gas emissions (GHG). At the same time the deep learning community began to realize that training models with more and more parameters required a lot of energy and as a consequence GHG emissions. To our knowledge, questioning the complete environmental impacts of AI methods for environment ("AI for green"), and not only GHG, has never been addressed directly. In this article we propose to study the possible negative impact of "AI for green" 1) by reviewing first the different types of AI impacts 2) by presenting the different methodologies used to assess those impacts, in particular life cycle assessment and 3) by discussing how to assess the environmental usefulness of a general AI service.

Despite the success of deep learning methods for semantic segmentation, few-shot semantic segmentation remains a challenging task due to the limited training data and the generalisation requirement for unseen classes. While recent progress has been particularly encouraging, we discover that existing methods tend to have poor performance in terms of meanIoU when query images contain other semantic classes besides the target class. To address this issue, we propose a novel self-supervised task that generates random pseudo-classes in the background of the query images, providing extra training data that would otherwise be unavailable when predicting individual target classes. To that end, we adopted superpixel segmentation for generating the pseudo-classes. With this extra supervision, we improved the meanIoU performance of the state-of-the-art method by 2.5% and 5.1% on the one-shot tasks, as well as 6.7% and 4.4% on the five-shot tasks, on the PASCAL-5i and COCO benchmarks, respectively.

This paper proposes a method to automatically detect the key feature parts in a CAD of commercial TV and monitor using a deep neural network. We developed a deep learning pipeline that can detect the injection parts such as hook, boss, undercut and press parts such as DPS, Embo-Screwless, Embo-Burring, and EMBO in the 2D CAD drawing images. We first cropped the drawing to a specific size for the training efficiency of a deep neural network. Then, we use Cascade R-CNN to find the position of injection and press parts and use Resnet-50 to predict the orientation of the parts. Finally, we convert the position of the parts found through the cropped image to the position of the original image. As a result, we obtained detection accuracy of injection and press parts with 84.1% in AP (Average Precision), 91.2% in AR(Average Recall), 72.0% in AP, 87.0% in AR, and orientation accuracy of injection and press parts with 94.4% and 92.0%, which can facilitate the faster design in industrial product design.