This paper describes a novel study on using `Attention Mask' input in transformers and using this approach for detecting offensive content in both English and Persian languages. The paper's principal focus is to suggest a methodology to enhance the performance of the BERT-based models on the `Offensive Language Detection' task. Therefore, we customize attention probabilities by changing the `Attention Mask' input to create more efficacious word embeddings. To do this, we firstly tokenize the training set of the exploited datasets (by BERT tokenizer). Then, we apply Multinomial Naive Bayes to map these tokens to two probabilities. These probabilities indicate the likelihood of making a text non-offensive or offensive, provided that it contains that token. Afterwards, we use these probabilities to define a new term, namely Offensive Score. Next, we create two separate (because of the differences in the types of the employed datasets) equations based on Offensive Scores for each language to re-distribute the `Attention Mask' input for paying more attention to more offensive phrases. Eventually, we put the F1-macro score as our evaluation metric and fine-tune several combinations of BERT with ANNs, CNNs and RNNs to examine the effect of using this methodology on various combinations. The results indicate that all models will enhance with this methodology. The most improvement was 2% and 10% for English and Persian languages, respectively.

Implicit deep learning has received increasing attention recently due to the fact that it generalizes the recursive prediction rules of many commonly used neural network architectures. Its prediction rule is provided implicitly based on the solution of an equilibrium equation. Although a line of recent empirical studies has demonstrated its superior performances, the theoretical understanding of implicit neural networks is limited. In general, the equilibrium equation may not be well-posed during the training. As a result, there is no guarantee that a vanilla (stochastic) gradient descent (SGD) training nonlinear implicit neural networks can converge. This paper fills the gap by analyzing the gradient flow of Rectified Linear Unit (ReLU) activated implicit neural networks. For an $m$-width implicit neural network with ReLU activation and $n$ training samples, we show that a randomly initialized gradient descent converges to a global minimum at a linear rate for the square loss function if the implicit neural network is \textit{over-parameterized}. It is worth noting that, unlike existing works on the convergence of (S)GD on finite-layer over-parameterized neural networks, our convergence results hold for implicit neural networks, where the number of layers is \textit{infinite}.

Understanding the fundamental mechanism behind the success of deep neural networks is one of the key challenges in the modern machine learning literature. Despite numerous attempts, a solid theoretical analysis is yet to be developed. In this paper, we develop a novel unified framework to reveal a hidden regularization mechanism through the lens of convex optimization. We first show that the training of multiple three-layer ReLU sub-networks with weight decay regularization can be equivalently cast as a convex optimization problem in a higher dimensional space, where sparsity is enforced via a group $\ell_1$-norm regularization. Consequently, ReLU networks can be interpreted as high dimensional feature selection methods. More importantly, we then prove that the equivalent convex problem can be globally optimized by a standard convex optimization solver with a polynomial-time complexity with respect to the number of samples and data dimension when the width of the network is fixed. Finally, we numerically validate our theoretical results via experiments involving both synthetic and real datasets.

Modern datasets often contain large subsets of correlated features and nuisance features, which are not or loosely related to the main underlying structures of the data. Nuisance features can be identified using the Laplacian score criterion, which evaluates the importance of a given feature via its consistency with the Graph Laplacians' leading eigenvectors. We demonstrate that in the presence of large numbers of nuisance features, the Laplacian must be computed on the subset of selected features rather than on the complete feature set. To do this, we propose a fully differentiable approach for unsupervised feature selection, utilizing the Laplacian score criterion to avoid the selection of nuisance features. We employ an autoencoder architecture to cope with correlated features, trained to reconstruct the data from the subset of selected features. Building on the recently proposed concrete layer that allows controlling for the number of selected features via architectural design, simplifying the optimization process. Experimenting on several real-world datasets, we demonstrate that our proposed approach outperforms similar approaches designed to avoid only correlated or nuisance features, but not both. Several state-of-the-art clustering results are reported.

Deep convolutional image classifiers progressively transform the spatial variability into a smaller number of channels, which linearly separates all classes. A fundamental challenge is to understand the role of rectifiers together with convolutional filters in this transformation. Rectifiers with biases are often interpreted as thresholding operators which improve sparsity and discrimination. This paper demonstrates that it is a different phase collapse mechanism which explains the ability to progressively eliminate spatial variability, while improving linear class separation. This is explained and shown numerically by defining a simplified complex-valued convolutional network architecture. It implements spatial convolutions with wavelet filters and uses a complex modulus to collapse phase variables. This phase collapse network reaches the classification accuracy of ResNets of similar depths, whereas its performance is considerably degraded when replacing the phase collapse with thresholding operators. This is justified by explaining how iterated phase collapses progressively improve separation of class means, as opposed to thresholding non-linearities.

Urban autonomous driving in the presence of pedestrians as vulnerable road users is still a challenging and less examined research problem. This work formulates navigation in urban environments as a multi objective reinforcement learning problem. A deep learning variant of thresholded lexicographic Q-learning is presented for autonomous navigation amongst pedestrians. The multi objective DQN agent is trained on a custom urban environment developed in CARLA simulator. The proposed method is evaluated by comparing it with a single objective DQN variant on known and unknown environments. Evaluation results show that the proposed method outperforms the single objective DQN variant with respect to all aspects.

Self-supervised learning (SSL) is a scalable way to learn general visual representations since it learns without labels. However, large-scale unlabeled datasets in the wild often have long-tailed label distributions, where we know little about the behavior of SSL. In this work, we systematically investigate self-supervised learning under dataset imbalance. First, we find out via extensive experiments that off-the-shelf self-supervised representations are already more robust to class imbalance than supervised representations. The performance gap between balanced and imbalanced pre-training with SSL is significantly smaller than the gap with supervised learning, across sample sizes, for both in-domain and, especially, out-of-domain evaluation. Second, towards understanding the robustness of SSL, we hypothesize that SSL learns richer features from frequent data: it may learn label-irrelevant-but-transferable features that help classify the rare classes and downstream tasks. In contrast, supervised learning has no incentive to learn features irrelevant to the labels from frequent examples. We validate this hypothesis with semi-synthetic experiments and theoretical analyses on a simplified setting. Third, inspired by the theoretical insights, we devise a re-weighted regularization technique that consistently improves the SSL representation quality on imbalanced datasets with several evaluation criteria, closing the small gap between balanced and imbalanced datasets with the same number of examples.

This article introduces a novel nonparametric methodology for Generalized Linear Models which combines the strengths of the binary regression and latent variable formulations for categorical data, while overcoming their disadvantages. Requiring minimal assumptions, it extends recently published parametric versions of the methodology and generalizes it. If the underlying data generating process is asymmetric, it gives uniformly better prediction and inference performance over the parametric formulation. Furthermore, it introduces a new classification statistic utilizing which I show that overall, it has better model fit, inference and classification performance than the parametric version, and the difference in performance is statistically significant especially if the data generating process is asymmetric. In addition, the methodology can be used to perform model diagnostics for any model specification. This is a highly useful result, and it extends existing work for categorical model diagnostics broadly across the sciences. The mathematical results also highlight important new findings regarding the interplay of statistical significance and scientific significance. Finally, the methodology is applied to various real-world datasets to show that it may outperform widely used existing models, including Random Forests and Deep Neural Networks with very few iterations.

Operator learning techniques have recently emerged as a powerful tool for learning maps between infinite-dimensional Banach spaces. Trained under appropriate constraints, they can also be effective in learning the solution operator of partial differential equations (PDEs) in an entirely self-supervised manner. In this work we analyze the training dynamics of deep operator networks (DeepONets) through the lens of Neural Tangent Kernel (NTK) theory, and reveal a bias that favors the approximation of functions with larger magnitudes. To correct this bias we propose to adaptively re-weight the importance of each training example, and demonstrate how this procedure can effectively balance the magnitude of back-propagated gradients during training via gradient descent. We also propose a novel network architecture that is more resilient to vanishing gradient pathologies. Taken together, our developments provide new insights into the training of DeepONets and consistently improve their predictive accuracy by a factor of 10-50x, demonstrated in the challenging setting of learning PDE solution operators in the absence of paired input-output observations. All code and data accompanying this manuscript are publicly available at \url{https://github.com/PredictiveIntelligenceLab/ImprovedDeepONets.}

Panaji: A team from Don Bosco College of Engineering, Fatorda, in a project sponsored by ISRO, has developed an algorithm that enables accurate identification of land features like forests, waterbodies, etc, using satellite images. Unlike applications like Google Earth, the machine-learning algorithm even helps identify details like the type of crops being cultivated in a field. The tool is expected to be immensely helpful in town and country planning, and in carrying out environmental studies, among other uses. Rahul Kotru, Musab Shaikh and Satyaswarup Banerjee of the electronics and telecommunication (ETC) branch have developed the deep learning algorithm, under the guidance of lead scientist, Varsha Turkar, who heads the department, and Shreyas Simu. This data can be captured during day and night independent of weather and climatic conditions.