This paper revisits the special type of a neural network known under two names. In the statistics and machine learning community it is known as a multi-class logistic regression neural network. In the neural network community, it is simply the soft-max layer. The importance is underscored by its role in deep learning: as the last layer, whose autput is actually the classification of the input patterns, such as images. Our exposition focuses on mathematically rigorous derivation of the key equation expressing the gradient. The fringe benefit of our approach is a fully vectorized expression, which is a basis of an efficient implementation. The second result of this paper is the positivity of the second derivative of the cross-entropy loss function as function of the weights. This result proves that optimization methods based on convexity may be used to train this network. As a corollary, we demonstrate that no $L^2$-regularizer is needed to guarantee convergence of gradient descent.

This paper presents a recognition system for handwritten Pashto letters. However, handwritten character recognition is a challenging task. These letters not only differ in shape and style but also vary among individuals. The recognition becomes further daunting due to the lack of standard datasets for inscribed Pashto letters. In this work, we have designed a database of moderate size, which encompasses a total of 4488 images, stemming from 102 distinguishing samples for each of the 44 letters in Pashto. The recognition framework uses zoning feature extractor followed by K-Nearest Neighbour (KNN) and Neural Network (NN) classifiers for classifying individual letter. Based on the evaluation of the proposed system, an overall classification accuracy of approximately 70.05% is achieved by using KNN while 72% is achieved by using NN.

The techniques of deep learning have become the state of the art methodology for executing complicated tasks from various domains of computer vision, natural language processing, and several other areas. Due to its rapid development and promising benchmarks in those fields, researchers started experimenting with this technique to perform in the area of, especially in intrusion detection related tasks. Deep learning is a subset and a natural extension of classical Machine learning and an evolved model of neural networks. This paper contemplates and discusses all the methodologies related to the leading edge Deep learning and Neural network models purposing to the arena of Intrusion Detection Systems.

Learning-based hashing algorithms are ``hot topics" because they can greatly increase the scale at which existing methods operate. In this paper, we propose a new learning-based hashing method called ``fast supervised discrete hashing" (FSDH) based on ``supervised discrete hashing" (SDH). Regressing the training examples (or hash code) to the corresponding class labels is widely used in ordinary least squares regression. Rather than adopting this method, FSDH uses a very simple yet effective regression of the class labels of training examples to the corresponding hash code to accelerate the algorithm. To the best of our knowledge, this strategy has not previously been used for hashing. Traditional SDH decomposes the optimization into three sub-problems, with the most critical sub-problem - discrete optimization for binary hash codes - solved using iterative discrete cyclic coordinate descent (DCC), which is time-consuming. However, FSDH has a closed-form solution and only requires a single rather than iterative hash code-solving step, which is highly efficient. Furthermore, FSDH is usually faster than SDH for solving the projection matrix for least squares regression, making FSDH generally faster than SDH. For example, our results show that FSDH is about 12-times faster than SDH when the number of hashing bits is 128 on the CIFAR-10 data base, and FSDH is about 151-times faster than FastHash when the number of hashing bits is 64 on the MNIST data-base. Our experimental results show that FSDH is not only fast, but also outperforms other comparative methods.

Estimating conditional dependence graphs and precision matrices are some of the most common problems in modern statistics and machine learning. When data are fully observed, penalized maximum likelihood-type estimators have become standard tools for estimating graphical models under sparsity conditions. Extensions of these methods to more complex settings where data are contaminated with additive or multiplicative noise have been developed in recent years. In these settings, however, the relative performance of different methods is not well understood and algorithmic gaps still exist. In particular, in high-dimensional settings these methods require using non-positive semidefinite matrices as inputs, presenting novel optimization challenges. We develop an alternating direction method of multipliers (ADMM) algorithm for these problems, providing a feasible algorithm to estimate precision matrices with indefinite input and potentially nonconvex penalties. We compare this method with existing alternative solutions and empirically characterize the tradeoffs between them. Finally, we use this method to explore the networks among US senators estimated from voting records data.

Acoustic scenes are rich and redundant in their content. In Given the rich content of acoustic scenes, they typically this work, we present a spatiotemporal attention pooling layer contain a lot of irrelevant and redundant information. This fact coupled with a convolutional recurrent neural network to learn naturally gives rise to the question of how to encourage a deep from patterns that are discriminative while suppressing those learning model to automatically discover and focus on discriminative that are irrelevant for acoustic scene classification. The convolutional patterns and suppress irrelevant ones from the acoustic layers in this network learn invariant features from scenes for better classification. We seek to address that question time-frequency input. The bidirectional recurrent layers are in this work using an attention mechanism [15]. To this end, we then able to encode the temporal dynamics of the resulting convolutional propose a spatiotemporal attention pooling layer in combination features. Afterwards, a two-dimensional attention with a convolutional recurrent neural network (CRNN), inspired mask is formed via the outer product of the spatial and temporal by their success in the audio event detection task [16, 17].

Recent work has shown that using unlabeled data in semi-supervised learning is not always beneficial and can even hurt generalization, especially when there is a class mismatch between the unlabeled and labeled examples. We investigate this phenomenon for image classification on the CIFAR-10 and the ImageNet datasets, and with many other forms of domain shifts applied (e.g. salt-and-pepper noise). Our main contribution is Split Batch Normalization (Split-BN), a technique to improve SSL when the additional unlabeled data comes from a shifted distribution. We achieve it by using separate batch normalization statistics for unlabeled examples. Due to its simplicity, we recommend it as a standard practice. Finally, we analyse how domain shift affects the SSL training process. In particular, we find that during training the statistics of hidden activations in late layers become markedly different between the unlabeled and the labeled examples.

In this paper, we describe our submission to SemEval-2019 Task 4 on Hyperpartisan News Detection. Our system relies on a variety of engineered features originally used to detect propaganda. This is based on the assumption that biased messages are propagandistic in the sense that they promote a particular political cause or viewpoint. We trained a logistic regression model with features ranging from simple bag-of-words to vocabulary richness and text readability features. Our system achieved 72.9% accuracy on the test data that is annotated manually and 60.8% on the test data that is annotated with distant supervision. Additional experiments showed that significant performance improvements can be achieved with better feature pre-processing.

Many vital tasks in network analysis involve prediction over edges and nodes. For instance in node classification, we aim at predicting most likely node's label. In a social network, this might be an interest or preference of the user, or in citation network, the research area the paper belongs to [7]. In link prediction, we intend to model the existence of a link between pair of nodes. Predicted links in social networks may denote real-life friends and in citation networks related but unmentioned references. It is recently recognized, that the majority of real-world networks are naturally dynamic. It means they evolve over time and nodes as well as links can appear or disappear. We know so far, that considering temporal information about the network allows their better understanding and modeling [9,16], especially for supervised machine learning tasks.

Learning good representations without supervision is still an open issue in machine learning, and is particularly challenging for speech signals, which are often characterized by long sequences with a complex hierarchical structure. Some recent works, however, have shown that it is possible to derive useful speech representations by employing a self-supervised encoder-discriminator approach. This paper proposes an improved self-supervised method, where a single neural encoder is followed by multiple workers that jointly solve different self-supervised tasks. The needed consensus across different tasks naturally imposes meaningful constraints to the encoder, contributing to discover general representations and to minimize the risk of learning superficial ones. Experiments show that the proposed approach can learn transferable, robust, and problem-agnostic features that carry on relevant information from the speech signal, such as speaker identity, phonemes, and even higher-level features such as emotional cues. In addition, a number of design choices make the encoder easily exportable, facilitating its direct usage or adaptation to different problems.