Learning the cumulative distribution function (CDF) of an outcome variable conditional on a set of features remains challenging, especially in high-dimensional settings. Conditional transformation models provide a semi-parametric approach that allows to model a large class of conditional CDFs without an explicit parametric distribution assumption and with only a few parameters. Existing estimation approaches within the class of transformation models are, however, either limited in their complexity and applicability to unstructured data sources such as images or text, or can incorporate complex effects of different features but lack interpretability. We close this gap by introducing the class of deep conditional transformation models which unify existing approaches and allow to learn both interpretable (non-)linear model terms and more complex predictors in one holistic neural network. To this end we propose a novel network architecture, provide details on different model definitions and derive suitable constraints and derive suitable network regularization terms. We demonstrate the efficacy of our approach through numerical experiments and applications.

Given a video with aligned dialogue, people can often infer what is more likely to happen next. Making such predictions requires not only a deep understanding of the rich dynamics underlying the video and dialogue, but also a significant amount of commonsense knowledge. In this work, we explore whether AI models are able to learn to make such multimodal commonsense next-event predictions. To support research in this direction, we collect a new dataset, named Video-and-Language Event Prediction (VLEP), with 28,726 future event prediction examples (along with their rationales) from 10,234 diverse TV Show and YouTube Lifestyle Vlog video clips. In order to promote the collection of non-trivial challenging examples, we employ an adversarial human-and-model-in-the-loop data collection procedure. We also present a strong baseline incorporating information from video, dialogue, and commonsense knowledge. Experiments show that each type of information is useful for this challenging task, and that compared to the high human performance on VLEP, our model provides a good starting point but leaves large room for future work. Our dataset and code are available at: https://github.com/jayleicn/VideoLanguageFuturePred

Online Social Media platforms (such as Twitter and Facebook) are extensively used for spreading the news to a wider public effortlessly at a rapid pace. However, now a days these platforms are also used with an aim of spreading rumors and fake news to a large audience in a short time span that can cause panic, fear, and financial loss to society. Thus, it is important to detect and control these rumors before it spreads to the masses. One way to control the spread of these rumors is by identifying possible suspicious users who are often involved in spreading the rumors. Our basic assumption is that the users who are often involved in spreading rumors are more likely to be suspicious in contrast to the users whose involvement in spreading rumors are less. This is due to the fact that sometimes, users may posts the rumor tweets by accident. In this paper, we use PHEME rumor tweet dataset which contains rumor and non-rumor tweets information on five incidents, that is, i) Charlie hebdo, ii)German wings crash, iii)Ottawa shooting, iv)Sydney siege, and v)Ferguson. We transform this rumor tweets dataset into suspicious users dataset before leveraging Graph Neural Network (GNN) based approach for identifying suspicious users. Specifically, we explore Graph Convolutional Network (GCN),which is a type of GNN, for identifying suspicious users and then we compare GCN results with the other three approaches which act as baseline approaches: SVM, RF and LSTM based deep learning architecture. Extensive experiments performed on real-world dataset, where we achieve up to 0.864 value for F1-Score and 0.720 value for AUC ROC, shows the effectiveness of GNN based approach for identifying suspicious users.

The introduction of artificial intelligence into activities traditionally carried out by human beings produces brutal changes. This is not without consequences for human values. This paper is about designing and implementing models of ethical behaviors in AI-based systems, and more specifically it presents a methodology for designing systems that take ethical aspects into account at an early stage while finding an innovative solution to prevent human values from being affected. Two case studies where AI-based innovations complement economic and social proposals with this methodology are presented: one in the field of culture and operated by a private company, the other in the field of scientific research and supported by a state organization.

This paper aims to explain deep neural networks (DNNs) from the perspective of multivariate interactions. In this paper, we define and quantify the significance of interactions among multiple input variables of the DNN. Input variables with strong interactions usually form a coalition and reflect prototype features, which are memorized and used by the DNN for inference. We define the significance of interactions based on the Shapley value, which is designed to assign the attribution value of each input variable to the inference. We have conducted experiments with various DNNs. Experimental results have demonstrated the effectiveness of the proposed method. Deep neural networks (DNNs) have exhibited significant success in many tasks, and the interpretability of DNNs has received increasing attention in recent years. Most previous studies of post-hoc explanation of DNNs either explain DNN semantically/visually Lundberg & Lee (2017); Ribeiro et al. (2016), or analyze the representation capacity of DNNs Higgins et al. (2017); Achille & Soatto (2018); Fort et al. (2019); Liang et al. (2019). In this paper, we propose a new perspective to explain a trained DNN, i.e. quantifying interactions among input variables that are used by the DNN during the inference process. Each input variable of a DNN usually does not work individually. Instead, input variables may cooperate with other variables to make inferences. We can consider the strongly interacted input variables to form a prototype feature (or a coalition), which is memorized by the DNN. For example, the face is a prototype feature for person detection, which is comprised of the eyes, nose, and mouth.

As you know, in supervised learning it is important for the data to be iid. In RL the training data is sampled from the state space that the agent chooses to explore, which tends to be highly correlated to the agent's current preferences and a small subset of the total state space. Q learning selects the action with the highest expected reward. So if a1 has an expected reward of 0.49, and a2 has an expected reward of 0.51, a small parameter change can cause the agent to swap from picking a2 100% of the time to picking a1 100% of the time, causing a significant shift in the distribution of data being trained on. At a higher conceptual level, you can think of RL as supervised learning where instead of having clearly defined labels, you'guess' what the label is using a often times noisy reward signal, and the quality of your guess is based on how accurate your policy is.

I think one thing that might help... look at it like this. A standard densely connected layer can represent a convolutional layer (standard'under the hood' implementation of convolution layers even converts it into a dense layer in a lot of cases so it can leverage fast matrix operations). In theory, if the dense layer can represent a convolutional layer, why's the convolutional layer used instead? You could just say that it's because there's less parameters, but it goes deeper than that. It'makes an assumption' that things likely to be seen in the dataset should be translation equivarient.

Is Bitcoin the revolution against unequal economic systems, or a scam and money laundry mechanism? Will artificial intelligence (AI) improve and boost humankind, or terminate our species? These questions present incompatible scenarios, but you will find supporters for all of them. They cannot be all right, so who's wrong then? Ideas spread because they are attractive, whether they are good or bad, right or wrong.

Since the beginning of the photography, Image colorization may have been reserved for those with artistic talent in the past, but now thanks to Artificial Intelligence, is it possible to colorize black and white images and video with outstanding quality. One interesting example is the paper Fully Automatic Video Colorization with Self-Regularization and Diversity ( you can read it here), which refers to one experiment by the Hong Kong University of Science and Technology, which presents a fully automatic method for colorizing black and white films without any human guidance or references. Typical image colorization methods require some sort of labeled reference. A key innovation of this paper is a novel framework consisting of a colorization network with self-learning techniques. The researchers used the ranked diversity loss function proposed in a CVPR paper to differentiate different solution modes.

Since introducing the Google News Initiative in 2018, the company has used the $300 million journalism project to fight disinformation and help publishers make money. Now, Google is also investing in journalism-specific software with Journalist Studio, a suite of free tools available to reporters and media organizations. The company says the new tools will aid investigative journalism and other projects that require sifting through vast troves of documents and data. The "anchor product" of Journalist Studio is Pinpoint, a tool that allows reporters and editors to more easily sift through documents, images and audio files. Pinpoint pulls out the names and locations that appear most often in any batch of documents, and allows you to dive into specific mentions of keywords in each file.