Deep neural network (DNN) and its variants have been extensively used for a wide spectrum of real applications such as image classification, face/speech recognition, fraud detection, and so on. In addition to many important machine learning tasks, as artificial networks emulating the way brain cells function, DNNs also show the capability of storing non-linear relationships between input and output data, which exhibits the potential of storing data via DNNs. We envision a new paradigm of data storage, "DNN-as-a-Database", where data are encoded in well-trained machine learning models. Compared with conventional data storage that directly records data in raw formats, learning-based structures (e.g., DNN) can implicitly encode data pairs of inputs and outputs and compute/materialize actual output data of different resolutions only if input data are provided. This new paradigm can greatly enhance the data security by allowing flexible data privacy settings on different levels, achieve low space consumption and fast computation with the acceleration of new hardware (e.g., Diffractive Neural Network and AI chips), and can be generalized to distributed DNN-based storage/computing. In this paper, we propose this novel concept of learning-based data storage, which utilizes a learning structure called learning-based memory unit (LMU), to store, organize, and retrieve data. As a case study, we use DNNs as the engine in the LMU, and study the data capacity and accuracy of the DNN-based data storage. Our preliminary experimental results show the feasibility of the learning-based data storage by achieving high (100%) accuracy of the DNN storage. We explore and design effective solutions to utilize the DNN-based data storage to manage and query relational tables. We discuss how to generalize our solutions to other data types (e.g., graphs) and environments such as distributed DNN storage/computing.

Injecting noise within gradient descent has several desirable features, such as smoothing and regularizing properties. In this paper, we investigate the effects of injecting noise before computing a gradient step. We demonstrate that small perturbations can induce explicit regularization for simple models based on the L1-norm, group L1-norms, or nuclear norms. However, when applied to overparametrized neural networks with large widths, we show that the same perturbations can cause variance explosion. To overcome this, we propose using independent layer-wise perturbations, which provably allow for explicit regularization without variance explosion. Our empirical results show that these small perturbations lead to improved generalization performance compared to vanilla gradient descent.

Entity coreference resolution is an important research problem with many applications, including information extraction and question answering. Coreference resolution for English has been studied extensively. However, there is relatively little work for other languages. A problem that frequently occurs when working with a non-English language is the scarcity of annotated training data. To overcome this challenge, we design a simple but effective ensemble-based framework that combines various transfer learning (TL) techniques. We first train several models using different TL methods. Then, during inference, we compute the unweighted average scores of the models' predictions to extract the final set of predicted clusters. Furthermore, we also propose a low-cost TL method that bootstraps coreference resolution models by utilizing Wikipedia anchor texts. Leveraging the idea that the coreferential links naturally exist between anchor texts pointing to the same article, our method builds a sizeable distantly-supervised dataset for the target language that consists of tens of thousands of documents. We can pre-train a model on the pseudo-labeled dataset before finetuning it on the final target dataset. Experimental results on two benchmark datasets, OntoNotes and SemEval, confirm the effectiveness of our methods. Our best ensembles consistently outperform the baseline approach of simple training by up to 7.68% in the F1 score. These ensembles also achieve new state-of-the-art results for three languages: Arabic, Dutch, and Spanish.

We work with many well-known firms around the world in private equity, investment banking, insurance, and asset management to apply Natural Language Processing and Artificial Intelligence algorithms to track e-reputation, competitive positioning, sentiment analysis, risk and ESG factors. SESAMm is growing quickly, with over 100 team members around the globe and offices in Paris, New York, London, Metz, Tunis, and Tokyo. Are you looking for a new challenge? Do you dream of joining a growing company, proposing new ideas, and taking part in innovative processes? At SESAMm, everyone brings their ideas, skills, and creativity.

Determining the author of a text is a difficult task. Here we compare multiple AI techniques for classifying literary texts written by multiple authors by taking into account a limited number of speech parts (prepositions, adverbs, and conjunctions). We also introduce a new dataset composed of texts written in the Romanian language on which we have run the algorithms. The compared methods are Artificial Neural Networks, Support Vector Machines, Multi Expression Programming, Decision Trees with C5.0, and k-Nearest Neighbour. Numerical experiments show, first of all, that the problem is difficult, but some algorithms are able to generate decent errors on the test set.

The challenges in applications of solar energy lies in its intermittency and dependency on meteorological parameters such as; solar radiation, ambient temperature, rainfall, wind-speed etc., and many other physical parameters like dust accumulation etc. Hence, it is important to estimate the amount of solar photovoltaic (PV) power generation for a specific geographical location. Machine learning (ML) models have gained importance and are widely used for prediction of solar power plant performance. In this paper, the impact of weather parameters on solar PV power generation is estimated by several Ensemble ML (EML) models like Bagging, Boosting, Stacking, and Voting for the first time. The performance of chosen ML algorithms is validated by field dataset of a 10kWp solar PV power plant in Eastern India region. Furthermore, a complete test-bed framework has been designed for data mining as well as to select appropriate learning models. It also supports feature selection and reduction for dataset to reduce space and time complexity of the learning models. The results demonstrate greater prediction accuracy of around 96% for Stacking and Voting EML models. The proposed work is a generalized one and can be very useful for predicting the performance of large-scale solar PV power plants also.

The often delightful and arresting images created by the latest generation of text-to-image generators, exemplified by DALL-E 2, Midjourney, and Stable Diffusion, have stirred up lots of buzz in both the arts and the AI worlds. The images, generated from simple text prompts (e.g., a baboon sailing a colorful dinghy), look very much like the products of intelligent human creativity. To explore just how creative these models really are and what they can teach us about the nature of our own innovative propensities, we asked four authorities on artificial intelligence, the brain, and creativity (and we also asked GPT-3, a language-generating model that's a close cousin to DALL-E) to explain what they think of DALL-E's capabilities and artistic potential. DALL-E starts by taking billions of bits of text from the internet and translating them into an abstraction, which it stores in a location in "latent," or logical, space. In the universe of describable things, for example, "baboon" will be "located" by strong associations near to other primates, probably not far from "Africa," "savanna," or "zoo."

Monkeypox is a rare disease that raised concern among medical specialists following the convi-19 pandemic. It's concerning since monkeypox is difficult to diagnose early on because of symptoms that are similar to chickenpox and measles. Furthermore, because this is a rare condition, there is a knowledge gap among healthcare professionals. As a result, there is an urgent need for a novel technique to combat and anticipate the disease in the early phases of individual virus infection. Multiple CNN-based pre-trained models, including VGG-16, VGG-19, Restnet50, Inception-V3, Densnet, Xception, MobileNetV2, Alexnet, Lenet, and majority Voting, were employed in classification in this study. For this study, multiple data sets were combined, such as monkeypox vs chickenpox, monkeypox versus measles, monkeypox versus normal, and monkeypox versus all diseases. Majority voting performed 97% in monkeypox vs chickenpox, Xception achieved 79% in monkeypox against measles, MobileNetV2 scored 96% in monkeypox vs normal, and Lenet performed 80% in monkeypox versus all.

Artificial Intelligence (AI) is a fast-growing area of study that stretching its presence to many business and research domains. Machine learning, deep learning, and natural language processing (NLP) are subsets of AI to tackle different areas of data processing and modelling. This review article presents an overview of AI impact on education outlining with current opportunities. In the education domain, student feedback data is crucial to uncover the merits and demerits of existing services provided to students. AI can assist in identifying the areas of improvement in educational infrastructure, learning management systems, teaching practices and study environment. NLP techniques play a vital role in analyzing student feedback in textual format. This research focuses on existing NLP methodologies and applications that could be adapted to educational domain applications like sentiment annotations, entity annotations, text summarization, and topic modelling. Trends and challenges in adopting NLP in education were reviewed and explored. Contextbased challenges in NLP like sarcasm, domain-specific language, ambiguity, and aspect-based sentiment analysis are explained with existing methodologies to overcome them. Research community approaches to extract the semantic meaning of emoticons and special characters in feedback which conveys user opinion and challenges in adopting NLP in education are explored.

Machine Learning (ML) methods, particularly generative models, are effective in addressing critical problems across different domains, which includes material sciences. Examples include the design of novel molecules by combining data-driven techniques and domain knowledge to efficiently search the space of all plausible molecules and generate new and valid ones [1, 2, 3, 4]. Traditional high-throughput wet-lab experiments, physics-based simulations, and bioinformatics tools for the molecular design process heavily depend on human expertise. These processes require significant resource expenditure to propose, synthesize and test new molecules, thereby limiting the exploration space [5, 6, 7]. For example, generative models have been applied to facilitate the material discovery process by employing inverse molecular design problem. This approach transforms the conventional and slow discovery process by mapping the desired set of properties to a set of structures. The generative process is then optimized to encourage the generation of molecules with those selected properties. Countless approaches have been suggested for such tasks, most prominently VAEs with different sampling techniques [8, 9, 10]), GANs [11, 12], diffusion models [13], flow networks [14] and Transformers [15].