Convolutional neural network (CNN) have proven its success for semantic segmentation, which is a core task of emerging industrial applications such as autonomous driving. However, most progress in semantic segmentation of urban scenes is reported on standard scenarios, i.e., daytime scenes with favorable illumination conditions. In practical applications, the outdoor weather and illumination are changeable, e.g., cloudy and nighttime, which results in a significant drop of semantic segmentation accuracy of CNN only trained with daytime data. In this paper, we propose a novel generative adversarial network (namely Mutual-GAN) to alleviate the accuracy decline when daytime-trained neural network is applied to videos captured under adverse weather conditions. The proposed Mutual-GAN adopts mutual information constraint to preserve image-objects during cross-weather adaptation, which is an unsolved problem for most unsupervised image-to-image translation approaches (e.g., CycleGAN). The proposed Mutual-GAN is evaluated on two publicly available driving video datasets (i.e., CamVid and SYNTHIA). The experimental results demonstrate that our Mutual-GAN can yield visually plausible translated images and significantly improve the semantic segmentation accuracy of daytime-trained deep learning network while processing videos under challenging weathers.

Social media platforms provide users the freedom of expression and a medium to exchange information and express diverse opinions. Unfortunately, this has also resulted in the growth of abusive content with the purpose of discriminating people and targeting the most vulnerable communities such as immigrants, LGBT, Muslims, Jews and women. Because abusive language is subjective in nature, there might be highly polarizing topics or events involved in the annotation of abusive contents such as hate speech (HS). Therefore, we need novel approaches to model conflicting perspectives and opinions coming from people with different personal and demographic backgrounds. In this paper, we present an in-depth study to model polarized opinions coming from different communities under the hypothesis that similar characteristics (ethnicity, social background, culture etc.) can influence the perspectives of annotators on a certain phenomenon. We believe that by relying on this information, we can divide the annotators into groups sharing similar perspectives. We can create separate gold standards, one for each group, to train state-of-the-art deep learning models. We can employ an ensemble approach to combine the perspective-aware classifiers from different groups to an inclusive model. We also propose a novel resource, a multi-perspective English language dataset annotated according to different sub-categories relevant for characterising online abuse: hate speech, aggressiveness, offensiveness and stereotype. By training state-of-the-art deep learning models on this novel resource, we show how our approach improves the prediction performance of a state-of-the-art supervised classifier.

Motivated by graph theory, artificial neural networks (ANNs) are traditionally structured as layers of neurons (nodes), which learn useful information by the passage of data through interconnections (edges). In the machine learning realm, graph structures (i.e., neurons and connections) of ANNs have recently been explored using various graph-theoretic measures linked to their predictive performance. On the other hand, in network science (NetSci), certain graph measures including entropy and curvature are known to provide insight into the robustness and fragility of real-world networks. In this work, we use these graph measures to explore the robustness of various ANNs to adversarial attacks. To this end, we (1) explore the design space of inter-layer and intra-layers connectivity regimes of ANNs in the graph domain and record their predictive performance after training under different types of adversarial attacks, (2) use graph representations for both inter-layer and intra-layers connectivity regimes to calculate various graph-theoretic measures, including curvature and entropy, and (3) analyze the relationship between these graph measures and the adversarial performance of ANNs. We show that curvature and entropy, while operating in the graph domain, can quantify the robustness of ANNs without having to train these ANNs. Our results suggest that the real-world networks, including brain networks, financial networks, and social networks may provide important clues to the neural architecture search for robust ANNs. We propose a search strategy that efficiently finds robust ANNs amongst a set of well-performing ANNs without having a need to train all of these ANNs.

To provide consistent emotional interaction with users, dialog systems should be capable to automatically select appropriate emotions for responses like humans. However, most existing works focus on rendering specified emotions in responses or empathetically respond to the emotion of users, yet the individual difference in emotion expression is overlooked. This may lead to inconsistent emotional expressions and disinterest users. To tackle this issue, we propose to equip the dialog system with personality and enable it to automatically select emotions in responses by simulating the emotion transition of humans in conversation. In detail, the emotion of the dialog system is transitioned from its preceding emotion in context. The transition is triggered by the preceding dialog context and affected by the specified personality trait. To achieve this, we first model the emotion transition in the dialog system as the variation between the preceding emotion and the response emotion in the Valence-Arousal-Dominance (VAD) emotion space. Then, we design neural networks to encode the preceding dialog context and the specified personality traits to compose the variation. Finally, the emotion for response is selected from the sum of the preceding emotion and the variation. We construct a dialog dataset with emotion and personality labels and conduct emotion prediction tasks for evaluation. Experimental results validate the effectiveness of the personality-affected emotion transition.

With the goal of making deep learning more label-efficient, a growing number of papers have been studying active learning (AL) for deep models. However, there are a number of issues in the prevalent experimental settings, mainly stemming from a lack of unified implementation and benchmarking. Issues in the current literature include sometimes contradictory observations on the performance of different AL algorithms, unintended exclusion of important generalization approaches such as data augmentation and SGD for optimization, a lack of study of evaluation facets like the labeling efficiency of AL, and little or no clarity on the scenarios in which AL outperforms random sampling (RS). In this work, we present a unified re-implementation of state-of-the-art AL algorithms in the context of image classification, and we carefully study these issues as facets of effective evaluation. On the positive side, we show that AL techniques are 2x to 4x more label-efficient compared to RS with the use of data augmentation. Surprisingly, when data augmentation is included, there is no longer a consistent gain in using BADGE, a state-of-the-art approach, over simple uncertainty sampling. We then do a careful analysis of how existing approaches perform with varying amounts of redundancy and number of examples per class. Finally, we provide several insights for AL practitioners to consider in future work, such as the effect of the AL batch size, the effect of initialization, the importance of retraining a new model at every round, and other insights.

The explosion in the sheer magnitude and complexity of financial news data in recent years makes it increasingly challenging for investment analysts to extract valuable insights and perform analysis. We propose FactCheck in finance, a web-based news aggregator with deep learning models, to provide analysts with a holistic view of important financial events from multilingual news sources and extract events using an unsupervised clustering method. A web interface is provided to examine the credibility of news articles using a transformer-based fact-checker. The performance of the fact checker is evaluated using a dataset related to merger and acquisition (M\&A) events and is shown to outperform several strong baselines.

The automatic recognition of food on images has numerous interesting applications, including nutritional tracking in medical cohorts. The problem has received significant research attention, but an ongoing public benchmark to develop open and reproducible algorithms has been missing. Here, we report on the setup of such a benchmark using publicly available food images sourced through the mobile MyFoodRepo app. Through four rounds, the benchmark released the MyFoodRepo-273 dataset constituting 24,119 images and a total of 39,325 segmented polygons categorized in 273 different classes. Models were evaluated on private tests sets from the same platform with 5,000 images and 7,865 annotations in the final round. Top-performing models on the 273 food categories reached a mean average precision of 0.568 (round 4) and a mean average recall of 0.885 (round 3). We present experimental validation of round 4 results, and discuss implications of the benchmark setup designed to increase the size and diversity of the dataset for future rounds.

GitHub and OpenAI have launched a technical preview of a new AI tool called Copilot, which lives inside the Visual Studio Code editor and autocompletes code snippets. Copilot does more than just parrot back code it's seen before, according to GitHub. It instead analyzes the code you've already written and generates new matching code, including specific functions that were previously called. Examples on the project's website include automatically writing the code to import tweets, draw a scatterplot, or grab a Goodreads rating. It works best with Python, JavaScript, TypeScript, Ruby, and Go, according to a blog post from GitHub CEO Nat Friedman. GitHub sees this as an evolution of pair programming, where two coders will work on the same project to catch each others' mistakes and speed up the development process.

I think a good reference to help in choosing between R and Python would be to take a look at the Data Science Lifecycle. Similar to any cycle, the Data Science lifecycle is an iterative process, each step will be continuously revisited when solving a business problem. Apart from'Business Understanding' each component will be a crucial factor in choosing between R and Python for a Data Science application. Personally, I prefer R when it comes to data preparation, EDA, and building less complex models. Performing statistical analysis is what R is recognized for across the industry, and its data visualization tools are a big part of it with libraries such as gg2plot.

Microsoft on Tuesday announced an artificial intelligence system that can recommend code for software developers to use as they write code. Microsoft is looking to simplify the process of programming, the area where the company got its start in 1975. That could keep programmers who already use the company's tools satisfied and also attract new ones. The system, called GitHub Copilot, draws on source code uploaded to code-sharing service GitHub, which Microsoft acquired in 2018, as well as other websites. Microsoft and GitHub developed it with help from OpenAI, an AI research start-up that Microsoft backed in 2019.