Effective human learning depends on a wide selection of educational materials that align with the learner's current understanding of the topic. While the Internet has revolutionized human learning or education, a substantial resource accessibility barrier still exists. Namely, the excess of online information can make it challenging to navigate and discover high-quality learning materials. In this paper, we propose the educational resource discovery (ERD) pipeline that automates web resource discovery for novel domains. The pipeline consists of three main steps: data collection, feature extraction, and resource classification. We start with a known source domain and conduct resource discovery on two unseen target domains via transfer learning. We first collect frequent queries from a set of seed documents and search on the web to obtain candidate resources, such as lecture slides and introductory blog posts. Then we introduce a novel pretrained information retrieval deep neural network model, query-document masked language modeling (QD-MLM), to extract deep features of these candidate resources. We apply a tree-based classifier to decide whether the candidate is a positive learning resource. The pipeline achieves F1 scores of 0.94 and 0.82 when evaluated on two similar but novel target domains. Finally, we demonstrate how this pipeline can benefit an application: leading paragraph generation for surveys. This is the first study that considers various web resources for survey generation, to the best of our knowledge. We also release a corpus of 39,728 manually labeled web resources and 659 queries from NLP, Computer Vision (CV), and Statistics (STATS).

Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks. Existing MTL works mainly focus on the scenario where label sets among multiple tasks (MTs) are usually the same, thus they can be utilized for learning across the tasks. While almost rare works explore the scenario where each task only has a small amount of training samples, and their label sets are just partially overlapped or even not. Learning such MTs is more challenging because of less correlation information available among these tasks. For this, we propose a framework to learn these tasks by jointly leveraging both abundant information from a learnt auxiliary big task with sufficiently many classes to cover those of all these tasks and the information shared among those partially-overlapped tasks. In our implementation of using the same neural network architecture of the learnt auxiliary task to learn individual tasks, the key idea is to utilize available label information to adaptively prune the hidden layer neurons of the auxiliary network to construct corresponding network for each task, while accompanying a joint learning across individual tasks. Our experimental results demonstrate its effectiveness in comparison with the state-of-the-art approaches.

Machine learning models may involve decision boundaries that change over time due to updates to rules and regulations, such as in loan approvals or claims management. However, in such scenarios, it may take time for sufficient training data to accumulate in order to retrain the model to reflect the new decision boundaries. While work has been done to reinforce existing decision boundaries, very little has been done to cover these scenarios where decision boundaries of the ML models should change in order to reflect new rules. In this paper, we focus on user-provided feedback rules as a way to expedite the ML models update process, and we formally introduce the problem of pre-processing training data to edit an ML model in response to feedback rules such that once the model is retrained on the pre-processed data, its decision boundaries align more closely with the rules. To solve this problem, we propose a novel data augmentation method, the Feedback Rule-Based Oversampling Technique. Extensive experiments using different ML models and real world datasets demonstrate the effectiveness of the method, in particular the benefit of augmentation and the ability to handle many feedback rules.

The article describes the approaches for forming different predictive features of tweet data sets and using them in the predictive analysis for decision-making support. The graph theory as well as frequent itemsets and association rules theory is used for forming and retrieving different features from these datasests. The use of these approaches makes it possible to reveal a semantic structure in tweets related to a specified entity. It is shown that quantitative characteristics of semantic frequent itemsets can be used in predictive regression models with specified target variables.

The paper describes the use of Bayesian regression for building time series models and stacking different predictive models for time series. Using Bayesian regression for time series modeling with nonlinear trend was analyzed. This approach makes it possible to estimate an uncertainty of time series prediction and calculate value at risk characteristics. A hierarchical model for time series using Bayesian regression has been considered. In this approach, one set of parameters is the same for all data samples, other parameters can be different for different groups of data samples. Such an approach allows using this model in the case of short historical data for specified time series, e.g. in the case of new stores or new products in the sales prediction problem. In the study of predictive models stacking, the models ARIMA, Neural Network, Random Forest, Extra Tree were used for the prediction on the first level of model ensemble. On the second level, time series predictions of these models on the validation set were used for stacking by Bayesian regression. This approach gives distributions for regression coefficients of these models. It makes it possible to estimate the uncertainty contributed by each model to stacking result. The information about these distributions allows us to select an optimal set of stacking models, taking into account the domain knowledge. The probabilistic approach for stacking predictive models allows us to make risk assessment for the predictions that are important in a decision-making process.

Anomalous pattern detection aims to identify instances where deviation from normalcy is evident, and is widely applicable across domains. Multiple anomalous detection techniques have been proposed in the state of the art. However, there is a common lack of a principled and scalable feature selection method for efficient discovery. Existing feature selection techniques are often conducted by optimizing the performance of prediction outcomes rather than its systemic deviations from the expected. In this paper, we proposed a sparsity-based automated feature selection (SAFS) framework, which encodes systemic outcome deviations via the sparsity of feature-driven odds ratios. SAFS is a model-agnostic approach with usability across different discovery techniques. SAFS achieves more than $3\times$ reduction in computation time while maintaining detection performance when validated on publicly available critical care dataset. SAFS also results in a superior performance when compared against multiple baselines for feature selection.

Acquiring information on large areas on the earth's surface through satellite cameras allows us to see much more than we can see while standing on the ground. This assists us in detecting and monitoring the physical characteristics of an area like land-use patterns, atmospheric conditions, forest cover, and many unlisted aspects. The obtained images not only keep track of continuous natural phenomena but are also crucial in tackling the global challenge of severe deforestation. Among which Amazon basin accounts for the largest share every year. Proper data analysis would help limit detrimental effects on the ecosystem and biodiversity with a sustainable healthy atmosphere. This report aims to label the satellite image chips of the Amazon rainforest with atmospheric and various classes of land cover or land use through different machine learning and superior deep learning models. Evaluation is done based on the F2 metric, while for loss function, we have both sigmoid cross-entropy as well as softmax cross-entropy. Images are fed indirectly to the machine learning classifiers after only features are extracted using pre-trained ImageNet architectures. Whereas for deep learning models, ensembles of fine-tuned ImageNet pre-trained models are used via transfer learning. Our best score was achieved so far with the F2 metric is 0.927.

Machine learning has become an essential part of contemporary software development and it often feels like another big buzzword. What are the challenges and common pitfalls? In this series of articles, I will go through the main strategies to test a program that contains some machine learning components. This first installment of the series is meant to introduce machine learning to the testing engineers/automation developers/performance engineers/ DevOps engineers, and then in the subsequent articles, I will tackle testing efforts on different levels. The best way to explain what machine learning is is to contrast it with classical computing -- AKA operative computing.

I've always believed that to truly learn data science you need to practice data science and I wanted to do this project to practice working with imbalanced classes in classification problems. This was also a perfect opportunity to start working with mlflow to help track my machine learning experiments: it allows me to track the different models I have used, the parameters I've trained with, and the metrics I've recorded. This project was aimed at predicting customer churn using the telecommunications data found on Kaggle [1] (which is a publicly available synthetic dataset). That is, we want to be able to predict if a given customer is going the leave the telecom provider based on the information we have on that customer. Now, why is this useful? Well, if we can predict which customers we think are going to leave before they leave then we can try to do something about it! For example, we could target them with specific offers, and maybe we could even use the model to provide us insight into what to offer them because we will know, or at least have an idea, as to why they are leaving.

Communication is defined as the act of sharing or exchanging information, ideas or feelings. To establish communication between two people, both of them are required to have knowledge and understanding of a common language. But in the case of deaf and dumb people, the means of communication are different. Deaf is the inability to hear and dumb is the inability to speak. They communicate using sign language among themselves and with normal people but normal people do not take seriously the importance of sign language. Not everyone possesses the knowledge and understanding of sign language which makes communication difficult between a normal person and a deaf and dumb person. To overcome this barrier, one can build a model based on machine learning. A model can be trained to recognize different gestures of sign language and translate them into English. This will help a lot of people in communicating and conversing with deaf and dumb people. The existing Indian Sing Language Recognition systems are designed using machine learning algorithms with single and double-handed gestures but they are not real-time. In this paper, we propose a method to create an Indian Sign Language dataset using a webcam and then using transfer learning, train a TensorFlow model to create a real-time Sign Language Recognition system. The system achieves a good level of accuracy even with a limited size dataset.