Recently, practical applications for passenger flow prediction have brought many benefits to urban transportation development. With the development of urbanization, a real-world demand from transportation managers is to construct a new metro station in one city area that never planned before. Authorities are interested in the picture of the future volume of commuters before constructing a new station, and estimate how would it affect other areas. In this paper, this specific problem is termed as potential passenger flow (PPF) prediction, which is a novel and important study connected with urban computing and intelligent transportation systems. For example, an accurate PPF predictor can provide invaluable knowledge to designers, such as the advice of station scales and influences on other areas, etc. To address this problem, we propose a multi-view localized correlation learning method. The core idea of our strategy is to learn the passenger flow correlations between the target areas and their localized areas with adaptive-weight. To improve the prediction accuracy, other domain knowledge is involved via a multi-view learning process. We conduct intensive experiments to evaluate the effectiveness of our method with real-world official transportation datasets. The results demonstrate that our method can achieve excellent performance compared with other available baselines. Besides, our method can provide an effective solution to the cold-start problem in the recommender system as well, which proved by its outperformed experimental results.

Question classification (QC) is the primary step of the Question Answering (QA) system. Question Classification (QC) system classifies the questions in particular classes so that Question Answering (QA) System can provide correct answers for the questions. Our system categorizes the factoid type questions asked in natural language after extracting features of the questions. We present a two stage QC system for Bengali. It utilizes one dimensional convolutional neural network for classifying questions into coarse classes in the first stage. Word2vec representation of existing words of the question corpus have been constructed and used for assisting 1D CNN. A smart data balancing technique has been employed for giving data hungry convolutional neural network the advantage of a greater number of effective samples to learn from. For each coarse class, a separate Stochastic Gradient Descent (SGD) based classifier has been used in order to differentiate among the finer classes within that coarse class. TF-IDF representation of each word has been used as feature for the SGD classifiers implemented as part of second stage classification. Experiments show the effectiveness of our proposed method for Bengali question classification.

I am training a XGBoost model using 5-fold croos validation on a very imbalanced binary classification problem. The dataset has 1200 columns (multi-document word2vec document embeddings). The reported performance on train data was extremely high (probably overfitting!!!): I know H2O cross validation generates an extra model using the whole data available and different performances are expected. But, could be the cause that generated too bad performance on the resulting model?

Automated Machine Learning (Auto ML) in Power BI is a powerful feature that is designed to automate the process of machine learning and allows users to successfully transform tasks like data imputation, feature engineering, model selection, training, testing and visualizing their results. Microsoft has introduced this incredibly smart feature to enable people with relatively little or no knowledge of Machine Learning. Auto ML is not only time-efficient, it also gets quality results in a reasonable amount of time for its users. It is important to understand that this feature, regardless of how innovative and efficient it is, does not replace all the machine learning techniques out there. In fact, there are many custom applications that cannot be applied to this feature.

Using the data available I will make a simple Logistic Regression model to predict the status of a show. For this analysis the training set is small but the model may still provide some insights as to the important features in Netflix's decision to Renew or End a show. Since the mean rating of renewed vs ended shows seems to be a major difference a very simple model which would be intuitive would be to predict a higher IMDB rating as renewed and a lower rating as ended. My model will take into account more features than just rating and hopefully will be able to provide some insights into why shows are renewed or ended by Netflix management. For how small the dataset is that I am working with and how simple the model is these accuracy scores are pretty good!

This course introduces the Scikit-learn library for doing Machine learning in Python.

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained model. This backdoor can then be activated during inference by a backdoor trigger to fully control the model's behavior. While such attacks are very effective, they crucially rely on the adversary injecting arbitrary inputs that are---often blatantly---mislabeled. Such samples would raise suspicion upon human inspection, potentially revealing the attack. Thus, for backdoor attacks to remain undetected, it is crucial that they maintain label-consistency---the condition that injected inputs are consistent with their labels. In this work, we leverage adversarial perturbations and generative models to execute efficient, yet label-consistent, backdoor attacks. Our approach is based on injecting inputs that appear plausible, yet are hard to classify, hence causing the model to rely on the (easier-to-learn) backdoor trigger.

Some veterans with a history of mild traumatic brain injury (mTBI) have reported experiencing auditory and visual dysfunction that persist beyond the acute phase of the incident. The etiology behind th ese symptoms is difficult to characterize, since mTBI is defined by negative imaging findings on current clinical imaging. There are several competing hypotheses that could explain functional deficits; one example is shear inju ry, which may manifest in dif fusion - weighted magnetic resonance (MR) imaging (DWI) . Herein, we explore this alternative hypothe sis in a pilot study of multi - parametric MR imaging. Briefly, we consider a cohort of 8 mTBI patients relative to 22 control subjects using structural T1 - weig hted imaging (T1w) and connectivity with DWI.

Convolutional neural network (CNN)-based feature learning has become state of the art, since given sufficient training data, CNN can significantly outperform traditional methods for various classification tasks. However, feature learning becomes more difficult if some training labels are noisy. With traditional regularization techniques, CNN often overfits to the noisy training labels, resulting in sub-par classification performance. In this paper, we propose a robust binary classifier, based on CNNs, to learn deep metric functions, which are then used to construct an optimal underlying graph structure used to clean noisy labels via graph Laplacian regularization (GLR). GLR is posed as a convex maximum a posteriori (MAP) problem solved via convex quadratic programming (QP). To penalize samples around the decision boundary, we propose two regularized loss functions for semi-supervised learning. The binary classification experiments on three datasets, varying in number and type of features, demonstrate that given a noisy training dataset, our proposed networks outperform several state-of-the-art classifiers, including label-noise robust support vector machine, CNNs with three different robust loss functions, model-based GLR, and dynamic graph CNN classifiers.

In this work we introduce the DP-auto-GAN framework for synthetic data generation, which combines the low dimensional representation of autoencoders with the flexibility of Generative Adversarial Networks (GANs). This framework can be used to take in raw sensitive data, and privately train a model for generating synthetic data that will satisfy the same statistical properties as the original data. This learned model can be used to generate arbitrary amounts of publicly available synthetic data, which can then be freely shared due to the post-processing guarantees of differential privacy. Our framework is applicable to unlabeled mixed-type data, that may include binary, categorical, and real-valued data. We implement this framework on both unlabeled binary data (MIMIC-III) and unlabeled mixed-type data (ADULT). We also introduce new metrics for evaluating the quality of synthetic mixed-type data, particularly in unsupervised settings.