Data streams are ubiquitous in modern business and society. In practice, data streams may evolve over time and cannot be stored indefinitely. Effective and transparent machine learning on data streams is thus often challenging. Hoeffding Trees have emerged as a state-of-the art for online predictive modelling. They are easy to train and provide meaningful convergence guarantees under a stationary process. Yet, at the same time, Hoeffding Trees often require heuristic and costly extensions to adjust to distributional change, which may considerably impair their interpretability. In this work, we revisit Model Trees for machine learning in evolving data streams. Model Trees are able to maintain more flexible and locally robust representations of the active data concept, making them a natural fit for data stream applications. Our novel framework, called Dynamic Model Tree, satisfies desirable consistency and minimality properties. In experiments with synthetic and real-world tabular streaming data sets, we show that the proposed framework can drastically reduce the number of splits required by existing incremental decision trees. At the same time, our framework often outperforms state-of-the-art models in terms of predictive quality -- especially when concept drift is involved. Dynamic Model Trees are thus a powerful online learning framework that contributes to more lightweight and interpretable machine learning in data streams.

The project, funded by Fonds de recherche du Québec – Nature et technologies (FRQNT), in partnership with the Ministère de l'Énergie et Ressources naturelles (MERN), under its second sustainable mining partnership research program, will analyze all airborne image data to predict the nature of the subsoil. The algorithms generated can be used as guides to target mineral exploration sites. This new approach to artificial intelligence aims to train parallel neural networks, each processing one type of variable, such as aeromagnetic or electromagnetic data. When processing is complete, a system will combine each network's predictions to generate a final prediction. Professor Gloaguen's team is working with experts in artificial intelligence applied to mining for this network development project, the first phase of which is already underway.

Higher education administrators can now look at chatbot technology as a tool they can use when planning strategies and initiatives geared toward student retention.

Data integration challenges are becoming more difficult as the volume of data available to large organizations continues to increase. Business leaders clearly understand that their data is of critical value but the volume, velocity, and variety of data available today is daunting. Faced with these challenges, companies are looking for solutions with a scalable, high-performing data integration approach to support a modern data architecture. The problem is that just as data integration is increasingly complex, the number of potential solutions is endless. From DIY products built by an army of developers to out-of-the-box solutions covering one or more use cases, it's difficult to navigate the myriad of choices and subsequent decision tree.

The growing digitization of nearly every aspect of our world and lives has created immense opportunities for the productive application of machine learning and data science. Organizations and institutions across the board are feeling the need to innovate and reinvent themselves by using artificial intelligence and putting their data to good use. And according to several surveys, data science is among the fastest-growing in-demand skills in different sectors. However, the growing demand for AI is hampered by the very low supply of data scientists and machine learning experts. Among the efforts to address this talent gap is the fast-evolving field of no-code AI, tools that make the creation and deployment of ML models accessible to organizations that don't have enough highly skilled data scientists and machine learning engineers.

Automatic segmentation of lung lesions associated with COVID-19 in CT images requires large amount of annotated volumes. Annotations mandate expert knowledge and are time-intensive to obtain through fully manual segmentation methods. Additionally, lung lesions have large inter-patient variations, with some pathologies having similar visual appearance as healthy lung tissues. This poses a challenge when applying existing semi-automatic interactive segmentation techniques for data labelling. To address these challenges, we propose an efficient convolutional neural networks (CNNs) that can be learned online while the annotator provides scribble-based interaction. To accelerate learning from only the samples labelled through user-interactions, a patch-based approach is used for training the network. Moreover, we use weighted cross-entropy loss to address the class imbalance that may result from user-interactions. During online inference, the learned network is applied to the whole input volume using a fully convolutional approach. We compare our proposed method with state-of-the-art using synthetic scribbles and show that it outperforms existing methods on the task of annotating lung lesions associated with COVID-19, achieving 16% higher Dice score while reducing execution time by 3$\times$ and requiring 9000 lesser scribbles-based labelled voxels. Due to the online learning aspect, our approach adapts quickly to user input, resulting in high quality segmentation labels. Source code for ECONet is available at: https://github.com/masadcv/ECONet-MONAILabel.

We investigate the optimal model size and number of tokens for training a transformer language model under a given compute budget. We find that current large language models are significantly undertrained, a consequence of the recent focus on scaling language models whilst keeping the amount of training data constant. By training over 400 language models ranging from 70 million to over 16 billion parameters on 5 to 500 billion tokens, we find that for compute-optimal training, the model size and the number of training tokens should be scaled equally: for every doubling of model size the number of training tokens should also be doubled. We test this hypothesis by training a predicted compute-optimal model, Chinchilla, that uses the same compute budget as Gopher but with 70B parameters and 4$\times$ more more data. Chinchilla uniformly and significantly outperforms Gopher (280B), GPT-3 (175B), Jurassic-1 (178B), and Megatron-Turing NLG (530B) on a large range of downstream evaluation tasks. This also means that Chinchilla uses substantially less compute for fine-tuning and inference, greatly facilitating downstream usage. As a highlight, Chinchilla reaches a state-of-the-art average accuracy of 67.5% on the MMLU benchmark, greater than a 7% improvement over Gopher.

The temporal answering grounding in the video (TAGV) is a new task naturally derived from temporal sentence grounding in the video (TSGV). Given an untrimmed video and a text question, this task aims at locating the matching span from the video that can semantically answer the question. Existing methods tend to formulate the TAGV task with a visual span-based question answering (QA) approach by matching the visual frame span queried by the text question. However, due to the weak correlations and huge gaps of the semantic features between the textual question and visual answer, existing methods adopting visual span predictor perform poorly in the TAGV task. To bridge these gaps, we propose a visual-prompt text span localizing (VPTSL) method, which introduces the timestamped subtitles as a passage to perform the text span localization for the input text question, and prompts the visual highlight features into the pre-trained language model (PLM) for enhancing the joint semantic representations. Specifically, the context query attention is utilized to perform cross-modal interaction between the extracted textual and visual features. Then, the highlight features are obtained through the video-text highlighting for the visual prompt. To alleviate semantic differences between textual and visual features, we design the text span predictor by encoding the question, the subtitles, and the prompted visual highlight features with the PLM. As a result, the TAGV task is formulated to predict the span of subtitles matching the visual answer. Extensive experiments on the medical instructional dataset, namely MedVidQA, show that the proposed VPTSL outperforms the state-of-the-art (SOTA) method by 28.36% in terms of mIOU with a large margin, which demonstrates the effectiveness of the proposed visual prompt and the text span predictor.

The impact of artificial intelligence as a powerful technology can be witnessed in diverse industry verticals. The education industry across the globe is no exception to this, with an increase in the use of AI by over 47.5 percent last year. The use of AI is in education has given a completely new perspective of looking at this field to teachers, students, parents, and of course the educational institutions as well. But it is also important to clarify to the public and the community that the purpose of Artificial Intelligence (AI) is about in education is not to replace teachers but to give them a helping hand in understanding the potential and limitations of each student. When we break down the benefits of Artificial intelligence (AI) is for students, we can come up with four categories, which are, personalization, tutoring, quick responses, and universal access.

R language is the world's most widely used programming language for statistical analysis, predictive modeling and data science. It's popularity is claimed in many recent surveys and studies. R programming language is getting powerful day by day as number of supported packages grows. Some of big IT companies such as Microsoft and IBM have also started developing packages on R and offering enterprise version of R. R is a free language and environment for statistical computing and graphics. You can perform a variety of tasks using R language.