Sex robots appear to be the next big thing for the adult entertainment industry. Unroboticized sex dolls are not new – but combined with state-of-the-art fabrication techniques, Artificial Intelligence (AI) and programming applications, such dolls may soon reach new levels of sophistication. As sex dolls become increasingly realistic – and their roboticization looms on the horizon – a key question to ask is how the law should respond when such objects are made for, and used by, those with a sexual interest in children? Dolls for this market, manufactured overseas, are now starting to appear on the legal radar from attempts to import them into the country. The National Crime Agency (NCA) has warned that child-like sex dolls are being sold on the internet and campaigners have urged the government to outlaw the trade.

For statistical models, selecting those predictors is what tests the steel of data scientists. It is really challenging to lay out the steps, as for every step, they should evaluate the situation and make decisions for the next or upcoming steps. It is a completely different story when running predictive models, and if relationship among the variables is not the main focus, situations get easier. Data analysts can go ahead to run step-wise regression models, empowering the data to give best predictions. However; if the main focus is on answering research questions that describe relationships, it can give analysts a really tough time.

Convolutional Neural Network (CNNs) are typically associated with Computer Vision. CNNs are responsible for major breakthroughs in Image Classification and are the core of most Computer Vision systems today. More recently CNNs have been applied to problems in Natural Language Processing and gotten some interesting results. In this paper, we will try to explain the basics of CNNs, its different variations and how they have been applied to NLP. This is a more concise survey than the paper below, and does a good job at 1/5 the length.

One of the main challenges in the parametrization of geological models is the ability to capture complex geological structures often observed in subsurface fields. In recent years, Generative Adversarial Networks (GAN) were proposed as an efficient method for the generation and parametrization of complex data, showing state-of-the-art performances in challenging computer vision tasks such as reproducing natural images (handwritten digits, human faces, etc.). In this work, we study the application of Wasserstein GAN for the parametrization of geological models. The effectiveness of the method is assessed for uncertainty propagation tasks using several test cases involving different permeability patterns and subsurface flow problems. Results show that GANs are able to generate samples that preserve the multipoint statistical features of the geological models both visually and quantitatively. The generated samples reproduce both the geological structures and the flow properties of the reference data.

A computationally simple genome-wide association study (GWAS) algorithm for estimating the main and epistatic effects of markers or single nucleotide polymorphisms (SNPs) is proposed. It is based on the intuitive assumption that changes of alleles corresponding to important SNPs in a pair of individuals lead to large difference of phenotype values of these individuals. The algorithm is based on considering pairs of individuals instead of SNPs or pairs of SNPs. The main advantage of the algorithm is that it weakly depends on the number of SNPs in a genotype matrix. It mainly depends on the number of individuals, which is typically very small in comparison with the number of SNPs. Numerical experiments with real data sets illustrate the proposed algorithm.

This paper studies the landscape of empirical risk of deep neural networks by theoretically analyzing its convergence behavior to the population risk as well as its stationary points and properties. For an $l$-layer linear neural network, we prove its empirical risk uniformly converges to its population risk at the rate of $\mathcal{O}(r^{2l}\sqrt{d\log(l)}/\sqrt{n})$ with training sample size of $n$, the total weight dimension of $d$ and the magnitude bound $r$ of weight of each layer. We then derive the stability and generalization bounds for the empirical risk based on this result. Besides, we establish the uniform convergence of gradient of the empirical risk to its population counterpart. We prove the one-to-one correspondence of the non-degenerate stationary points between the empirical and population risks with convergence guarantees, which describes the landscape of deep neural networks. In addition, we analyze these properties for deep nonlinear neural networks with sigmoid activation functions. We prove similar results for convergence behavior of their empirical risks as well as the gradients and analyze properties of their non-degenerate stationary points. To our best knowledge, this work is the first one theoretically characterizing landscapes of deep learning algorithms. Besides, our results provide the sample complexity of training a good deep neural network. We also provide theoretical understanding on how the neural network depth $l$, the layer width, the network size $d$ and parameter magnitude determine the neural network landscapes.

Categorical variables are a natural choice for representing discrete structure in the world. However, stochastic neural networks rarely use categorical latent variables due to the inability to backpropagate through samples. In this work, we present an efficient gradient estimator that replaces the non-differentiable sample from a categorical distribution with a differentiable sample from a novel Gumbel-Softmax distribution. This distribution has the essential property that it can be smoothly annealed into a categorical distribution. We show that our Gumbel-Softmax estimator outperforms state-of-the-art gradient estimators on structured output prediction and unsupervised generative modeling tasks with categorical latent variables, and enables large speedups on semi-supervised classification.

Noname manuscript No. (will be inserted by the editor) Abstract Label embedding (LE) is an important family of multi-label classification algorithms that digest the label information jointly for better performance. Different real-world applications evaluate performance by different cost functions of interest. Current LE algorithms often aim to optimize one specific cost function, but they can suffer from bad performance with respect to other cost functions. In this paper, we resolve the performance issue by proposing a novel cost-sensitive LE algorithm that takes the cost function of interest into account. The proposed algorithm, cost-sensitive label embedding with multidimensional scaling (CLEMS), approximates the cost information with the distances of the embedded vectors by using the classic multidimensional scaling approach for manifold learning. CLEMS is able to deal with both symmetric and asymmetric cost functions, and effectively makes cost-sensitive decisions by nearest-neighbor decoding within the embedded vectors. We derive theoretical results that justify how CLEMS achieves the desired cost-sensitivity. Furthermore, extensive experimental results demonstrate that CLEMS is significantly better than a wide spectrum of existing LE algorithms and state-of-the-art cost-sensitive algorithms across different cost functions. Keywords Multi-label classification, Cost-sensitive, Label embedding 1 Introduction The multi-label classification problem (MLC), which allows multiple labels to be associated with each example, is an extension of the multi-class classification problem.

Connections between relations in relation extraction, which we call class ties, are common. In distantly supervised scenario, one entity tuple may have multiple relation facts. Exploiting class ties between relations of one entity tuple will be promising for distantly supervised relation extraction. However, previous models are not effective or ignore to model this property. In this work, to effectively leverage class ties, we propose to make joint relation extraction with a unified model that integrates convolutional neural network (CNN) with a general pairwise ranking framework, in which three novel ranking loss functions are introduced. Additionally, an effective method is presented to relieve the severe class imbalance problem from NR (not relation) for model training. Experiments on a widely used dataset show that leveraging class ties will enhance extraction and demonstrate the effectiveness of our model to learn class ties. Our model outperforms the baselines significantly, achieving state-of-the-art performance.

Flexible endoscopes can snake through narrow passages to treat difficult to reach areas of the body. However, once they arrive at their target, these devices rely on rigid surgical tools to manipulate or remove tissue. These tools offer surgeons reduced dexterity and sensing, limiting the current therapeutic capabilities of the endoscope. Now, researchers from the Wyss Institute for Biologically Inspired Engineering at Harvard University and the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS) have developed a hybrid rigid-soft robotic arm for endoscopes with integrated sensing, flexibility, and multiple degrees of freedom. This arm -- built using a manufacturing paradigm based on pop-up fabrication and soft lithography -- lies flat on an endoscope until it arrives at the desired spot, then pops up to assist in surgical procedures.