Natural language processing (NLP) has a significant impact on society via technologies such as machine translation and search engines. Despite its success, NLP technology is only widely available for high-resource languages such as English and Chinese, while it remains inaccessible to many languages due to the unavailability of data resources and benchmarks. In this work, we focus on developing resources for languages in Indonesia. Despite being the second most linguistically diverse country, most languages in Indonesia are categorized as endangered and some are even extinct. We develop the first-ever parallel resource for 10 low-resource languages in Indonesia. Our resource includes datasets, a multi-task benchmark, and lexicons, as well as a parallel Indonesian-English dataset. We provide extensive analyses and describe the challenges when creating such resources. We hope that our work can spark NLP research on Indonesian and other underrepresented languages.

Facial expression is one of the most powerful, natural, and universal signals for human beings to express emotional states and intentions. Thus, it is evident the importance of correct and innovative facial expression recognition (FER) approaches in Artificial Intelligence. The current common practice for FER is to correctly design convolutional neural networks' architectures (CNNs) using human expertise. However, finding a well-performing architecture is often a very tedious and error-prone process for deep learning researchers. Neural architecture search (NAS) is an area of growing interest as demonstrated by the large number of scientific works published in recent years thanks to the impressive results achieved in recent years. We propose a genetic algorithm approach that uses an ingenious encoding-decoding mechanism that allows to automatically evolve CNNs on FER tasks attaining high accuracy classification rates. The experimental results demonstrate that the proposed algorithm achieves the best-known results on the CK+ and FERG datasets as well as competitive results on the JAFFE dataset.

This is the official application form for the Ghana Data Science Summit 2023 (IndabaX Ghana). Date of Conference: Saturday, 13th May, 2023 Venue: Methodist University College, Accra Please read the following general instructions/comments before completing the application: (1) Please respond to as many questions as you can in a truthful manner. (2) All applications will be reviewed by the organizing team and decisions made based on interest and academic and professional background. If you are new to this field, you are still welcome to apply. (3) Admission to the conference is free but you must be accepted by the organizing team to attend. (4) Please submit only ONE application. Multiple applications will be disqualified. (5) This year's conference will take place in one day and will comprise a hands-on tutorials session, a hackathon and poster presentations. You will be asked to indicate your interest in this form. Kindly note that you can either choose the hands-on tutorial session OR the hackathon and NOT BOTH. Also, regardless of the option you choose, you can submit a proposal for a poster presentation. Hands-On Tutorials (Recommended for Beginners) The hands-on tutorial will cover basics in Python programming useful for Machine Learning. We would cover topics like Python Lists, Introduction to Numpy, and Introduction to Scikit-Learn. Additionally, we would go over a practical project using Python. This project will guide you in a step-by-step process of building a Machine Learning Project with Python. We encourage all participants who would be selected to participate to bring along their laptops. No prior knowledge of Python programming or Machine Learning is required. Hackathon (Recommended for Intermediates and Experts) The Hackathon will be based on a practical Machine Learning project where you would have access to a starter notebook. You will be required to work in a team to come up with a better solution that can get the best score on the leaderboard. All selected participants are highly encouraged to come along with their laptops to participate in the competition. We would also not be providing any GPUs as you will not necessarily need this in the Hackathon. Advanced or intermediate knowledge in Python programming and machine learning is highly required. Prizes will be awarded to the best 3 teams on the leaderboard. (6) Kindly email us via info@indabaxghana.com if you have any questions. www.indabaxghana.com

Much of the conversation around artificial intelligence (AI) these days centers on whether it will eventually take your job, how it's trying to compete with humans in creative fields, or how it can be misused, say, as a writing tool. You can probably chalk this one-sidedness up to an all-too-human tendency to be suspicious of new tech that isn't well understood by the mainstream (yet). But AI isn't intrinsically evil or good: It's a tool, a vast technology with enormous potential, and there are myriad ways to implement it beyond the current discourse. One vitally important use case is helping us fight and survive the consequences of climate change. Whether it's mitigating the effects of disasters such as floods and fires more quickly or building a cleaner energy grid, the evidence is mounting that AI has an essential role to play in helping to protect us as the planet reacts to climate change. And we'll need all the help we can get.

ChatGPT is an AI-powered conversational model developed by OpenAI that has revolutionized the way we communicate with machines. However, like any new technology, there are potential risks and dangers associated with its use. In this article, we will explore the dark side of ChatGPT AI technology and discuss the unseen dangers that lurk beneath its seemingly harmless exterior. The chatbot you are using has been trained on a lot of information from different sources like books, websites, social media posts, and articles on the internet. There's a chance that it has even been trained on your own social media posts. It's not clear if the company behind the chatbot got permission from the original authors to use their information.

This article presents a novel hybrid approach using statistics and machine learning to forecast the national demand of electricity. As investment and operation of future energy systems require long-term electricity demand forecasts with hourly resolution, our mathematical model fills a gap in energy forecasting. The proposed methodology was constructed using hourly data from Ukraine's electricity consumption ranging from 2013 to 2020. To this end, we analysed the underlying structure of the hourly, daily and yearly time series of electricity consumption. The long-term yearly trend is evaluated using macroeconomic regression analysis. The mid-term model integrates temperature and calendar regressors to describe the underlying structure, and combines ARIMA and LSTM ``black-box'' pattern-based approaches to describe the error term. The short-term model captures the hourly seasonality through calendar regressors and multiple ARMA models for the residual. Results show that the best forecasting model is composed by combining multiple regression models and a LSTM hybrid model for residual prediction. Our hybrid model is very effective at forecasting long-term electricity consumption on an hourly resolution. In two years of out-of-sample forecasts with 17520 timesteps, it is shown to be within 96.83 \% accuracy.

In this proposed work, we identified the significant research issues on lung cancer risk factors. Capturing and defining symptoms at an early stage is one of the most difficult phases for patients. Based on the history of patients records, we reviewed a number of current research studies on lung cancer and its various stages. We identified that lung cancer is one of the significant research issues in predicting the early stages of cancer disease. This research aimed to develop a model that can detect lung cancer with a remarkably high level of accuracy using the deep learning approach (convolution neural network). This method considers and resolves significant gaps in previous studies. We compare the accuracy levels and loss values of our model with VGG16, InceptionV3, and Resnet50. We found that our model achieved an accuracy of 94% and a minimum loss of 0.1%. Hence physicians can use our convolution neural network models for predicting lung cancer risk factors in the real world. Moreover, this investigation reveals that squamous cell carcinoma, normal, adenocarcinoma, and large cell carcinoma are the most significant risk factors. In addition, the remaining attributes are also crucial for achieving the best performance.

We focus on learning composable policies to control a variety of physical agents with possibly different structures. Among state-of-the-art methods, prominent approaches exploit graph-based representations and weight-sharing modular policies based on the message-passing framework. However, as shown by recent literature, message passing can create bottlenecks in information propagation and hinder global coordination. This drawback can become even more problematic in tasks where high-level planning is crucial. In fact, in similar scenarios, each modular policy - e.g., controlling a joint of a robot - would request to coordinate not only for basic locomotion but also achieve high-level goals, such as navigating a maze. A classical solution to avoid similar pitfalls is to resort to hierarchical decision-making. In this work, we adopt the Feudal Reinforcement Learning paradigm to develop agents where control actions are the outcome of a hierarchical (pyramidal) message-passing process. In the proposed Feudal Graph Reinforcement Learning (FGRL) framework, high-level decisions at the top level of the hierarchy are propagated through a layered graph representing a hierarchy of policies. Lower layers mimic the morphology of the physical system and upper layers can capture more abstract sub-modules. The purpose of this preliminary work is to formalize the framework and provide proof-of-concept experiments on benchmark environments (MuJoCo locomotion tasks). Empirical evaluation shows promising results on both standard benchmarks and zero-shot transfer learning settings.

Convolutional neural networks are now seeing widespread use in a variety of fields, including image classification, facial and object recognition, medical imaging analysis, and many more. In addition, there are applications such as physics-informed simulators in which accurate forecasts in real time with a minimal lag are required. The present neural network designs include millions of parameters, which makes it difficult to install such complex models on devices that have limited memory. Compression techniques might be able to resolve these issues by decreasing the size of CNN models that are created by reducing the number of parameters that contribute to the complexity of the models. We propose a compressed tensor format of convolutional layer, a priori, before the training of the neural network. 3-way kernels or 2-way kernels in convolutional layers are replaced by one-way fiters. The overfitting phenomena will be reduced also. The time needed to make predictions or time required for training using the original Convolutional Neural Networks model would be cut significantly if there were fewer parameters to deal with. In this paper we present a method of a priori compressing convolutional neural networks for finite element (FE) predictions of physical data. Afterwards we validate our a priori compressed models on physical data from a FE model solving a 2D wave equation. We show that the proposed convolutinal compression technique achieves equivalent performance as classical convolutional layers with fewer trainable parameters and lower memory footprint.

Attitude is omnipresent in almost every type of text. There has yet to be any relevant research on attitudinal shifts in self-translation. The Chinese version of Between Tears and Laughter is a rare case of self-translation and co-translation in that the first 11 chapters are self-translated by Lin Yutang, and the last 12 chapters by Xu Chengbin. The current study conducted a word frequency analysis of this book's English and Chinese versions with LIWC and AntConc, and made comparative research into Lin Yutang's attitudinal changes. The results show that due to different writing purposes and readerships, there is less anger in Lin's self-translation (M=0.7755, SD=0.3861), which is a significant difference (t=2.2892, This attitudinal change is also reflected in the translations of some n-grams containing anger words. In contrast, there is no significant difference (t=1.88, This paper believes that corpus tools can help co-translators keep their translation consistent in attitude. Introduction Lin Yutang (1895 - 1976), the author of My Country and My People and Moment in Peking, was a world-renowned Chinese writer publishing novels, essays, translations, textbooks, and Chinese-English dictionaries, making outstanding achievements in literature, translation, and language research. He even invented a Chinese typewriter. He wrote more than 30 books in English, most of which describe China's cultural aspects. According to the biography of Lin Yutang written by his daughter Lin Taiyi, Lin was nominated twice for the Nobel Prize for Literature (Lin 1989).