One and two are pre-trained deep learning models, meaning that they are provided to you as-is by OpenCV. The Movidius NCS will perform inference using each of these models. The third recognizer model is not a form of deep learning. Rather, it is our SVM machine learning face recognition model. The RPi CPU will have to handle making face recognition predictions using it. We also load our label encoder which holds the names of the people our model can recognize (Line 42). Let's initialize our video stream: Line 47 initializes and starts our VideoStream object. We wait for the camera sensor to warm up on Line 48. Line 51 initializes our FPS counter for benchmarking purposes.

Identifying the underlying directional relations from observational time series with nonlinear interactions and complex relational structures is key to a wide range of applications, yet remains a hard problem. In this work, we introduce a novel minimum predictive information regularization method to infer directional relations from time series, allowing deep learning models to discover nonlinear relations. Our method substantially outperforms other methods for learning nonlinear relations in synthetic datasets, and discovers the directional relations in a video game environment and a heart-rate vs. breath-rate dataset.

We study clustering methods for binary data, first defining aggregation criteria that measure the compactness of clusters. Five new and original methods are introduced, using neighborhoods and population behavior combinatorial optimization metaheuristics: first ones are simulated annealing, threshold accepting and tabu search, and the others are a genetic algorithm and ant colony optimization. The methods are implemented, performing the proper calibration of parameters in the case of heuristics, to ensure good results. From a set of 16 data tables generated by a quasi-Monte Carlo experiment, a comparison is performed for one of the aggregations using L1 dissimilarity, with hierarchical clustering, and a version of k-means: partitioning around medoids or PAM. Simulated annealing perform very well, especially compared to classical methods.

The tremendous increase in the amount of available research documents impels researchers to propose topic models to extract the latent semantic themes of a documents collection. However, how to extract the hidden topics of the documents collection has become a crucial task for many topic model applications. Moreover, conventional topic modeling approaches suffer from the scalability problem when the size of documents collection increases. In this paper, the Correlated Topic Model with variational Expectation-Maximization algorithm is implemented in MapReduce framework to solve the scalability problem. The proposed approach utilizes the dataset crawled from the public digital library. In addition, the full-texts of the crawled documents are analysed to enhance the accuracy of MapReduce CTM. The experiments are conducted to demonstrate the performance of the proposed algorithm. From the evaluation, the proposed approach has a comparable performance in terms of topic coherences with LDA implemented in MapReduce framework.

Federated learning is an emerging research paradigm to train models on private data distributed over multiple devices. A key challenge involves keeping private all the data on each device and training a global model only by communicating parameters and updates. Overcoming this problem relies on the global model being sufficiently compact so that the parameters can be efficiently sent over communication channels such as wireless internet. Given the recent trend towards building deeper and larger neural networks, deploying such models in federated settings on real-world tasks is becoming increasingly difficult. To this end, we propose to augment federated learning with local representation learning on each device to learn useful and compact features from raw data. As a result, the global model can be smaller since it only operates on higher-level local representations. We show that our proposed method achieves superior or competitive results when compared to traditional federated approaches on a suite of publicly available real-world datasets spanning image recognition (MNIST, CIFAR) and multimodal learning (VQA). Our choice of local representation learning also reduces the number of parameters and updates that need to be communicated to and from the global model, thereby reducing the bottleneck in terms of communication cost. Finally, we show that our local models provide flexibility in dealing with online heterogeneous data and can be easily modified to learn fair representations that obfuscate protected attributes such as race, age, and gender, a feature crucial to preserving the privacy of on-device data.

We study system design problems stated as parameterized stochastic programs with a chance-constraint set. We adopt a Bayesian approach that requires the computation of a posterior predictive integral which is usually intractable. In addition, for the problem to be a well-defined convex program, we must retain the convexity of the feasible set. Consequently, we propose a variational Bayes-based method to approximately compute the posterior predictive integral that ensures tractability and retains the convexity of the feasible set. Under certain regularity conditions, we also show that the solution set obtained using variational Bayes converges to the true solution set as the number of observations tends to infinity. We also provide bounds on the probability of qualifying a true infeasible point (with respect to the true constraints) as feasible under the VB approximation for a given number of samples.

Its impact is drastic and real: Youtube's AIdriven recommendation system would present sports videos for days if one happens to watch a live baseball game on the platform [1]; email writing becomes much faster with machine learning (ML) based auto-completion [2]; many businesses have adopted natural language processing based chatbots as part of their customer services [3]. AI has also greatly advanced human capabilities in complex decision-making processes ranging from determining how to allocate security resources to protect airports [4] to games such as poker [5] and Go [6]. All such tangible and stunning progress suggests that an "AI summer" is happening. As some put it, "AI is the new electricity" [7]. Meanwhile, in the past decade, an emerging theme in the AI research community is the so-called "AI for social good" (AI4SG): researchers aim at developing AI methods and tools to address problems at the societal level and improve the wellbeing of the society.

This paper proposes a novel method for privacy-preserving release of an entire dataset while maintaining useful properties, such as statistics required for reconstructing a support vector machine classifier. This is done by balancing privacy and utility guarantees using an explicit optimization problem. The dataset is systematically obfuscated using an additive noise and the inverse of the trace of the Fisher information matrix is used as a measure of privacy for the entries of the dataset. By the use of the Cramér-Rao bound [3, p. 169] The use of the Fisher information matrix makes the privacy metric independent of the sophistication of the adversary, thus making it a universal measure of privacy. Further, the Cramér-Rao bound provides a practical/operational interpretation of the measure of privacy to the data owners, i.e., how much someone can learn about an individual in the dataset based on the publicly released obfuscated data.

In practice, however, we frequently encounter training data with a class-imbalanced distribution . For example, modern real-world large-scale datasets often have the so-called long-tailed distribution: a few major classes claim most of the instances, while most of the other minor classes are represented by relatively fewer instances [16, 31, 38, 50, 51, 61]. Classifiers trained with this kind of datasets using conventional strategies (e.g., mini-batch SGD on uniformly sampled instances) have been found to perform poorly on minor classes [3, 19, 40, 52], which is particularly unfavorable if we evaluate the classifiers with class-balanced test data or average per-class accuracy. One common explanation to the poor performance is the Figure 1: Over-fitting to minor classes and feature deviation: (top-left) the number of training (red) and test (blue) instances per class of an imbalanced CIFAR-10 [8, 32]; (top-right) the training and test set accuracy per class using a ResNet [20]; (bottom) the t-SNE [41] plot of the training (circle) and test (cross) features before the last linear classifier layer. We see a trend of over-fitting to minor classes, which results from the feature deviation of training and test instances (see the magenta and red minor classes).

We determine the cutoff value on separation of cluster centers for exact recovery of cluster labels in a $K$-component Gaussian mixture model with equal cluster sizes. Moreover, we show that a semidefinite programming (SDP) relaxation of the $K$-means clustering method achieves such sharp threshold for exact recovery without assuming the symmetry of cluster centers.