The ability to match pieces of code to their corresponding natural language descriptions and vice versa is fundamental for natural language search interfaces to software repositories. In this paper, we propose a novel multi-perspective cross-lingual neural framework for code--text matching, inspired in part by a previous model for monolingual text-to-text matching, to capture both global and local similarities. Our experiments on the CoNaLa dataset show that our proposed model yields better performance on this cross-lingual text-to-code matching task than previous approaches that map code and text to a single joint embedding space.

Convolutional neural network (CNN), with ability of feature learning and nonlinear mapping, has demonstrated its effectiveness in prognostics and health management (PHM). However, explanation on the physical meaning of a CNN architecture has rarely been studied. In this paper, a novel wavelet driven deep neural network termed as WaveletKernelNet (WKN) is presented, where a continuous wavelet convolutional (CWConv) layer is designed to replace the first convolutional layer of the standard CNN. This enables the first CWConv layer to discover more meaningful filters. Furthermore, only the scale parameter and translation parameter are directly learned from raw data at this CWConv layer. This provides a very effective way to obtain a customized filter bank, specifically tuned for extracting defect-related impact component embedded in the vibration signal. In addition, three experimental verification using data from laboratory environment are carried out to verify effectiveness of the proposed method for mechanical fault diagnosis. The results show the importance of the designed CWConv layer and the output of CWConv layer is interpretable. Besides, it is found that WKN has fewer parameters, higher fault classification accuracy and faster convergence speed than standard CNN.

The deep learning algorithm, developed by researchers at the Boston University School of Medicine, uses a combination of brain magnetic resonance imaging (MRI) testing to measure cognitive impairment, along with data on age and gender, which helps to accurately predict the risk of Alzheimer's Disease. Alzheimer's disease is the primary cause of dementia worldwide. One in 10 people age 65 and older has Alzheimer's dementia and it is the primary cause of dementia worldwide. The study has been published in the journal Brain. The researchers used MRI scans of the brain, demographics, and clinical information of individuals with Alzheimer's disease as well as ones with normal cognition.

OpenAI today announced it will begin tracking machine learning models that achieve state-of-the-art efficiency, an effort it believes will help identify candidates for scaling and achieving top overall performance. To kick-start things, the firm published an analysis suggesting that since 2012, the amount of compute needed to train an AI model to the same performance on classifying images in a popular benchmark -- ImageNet -- has been decreasing by a factor of 2 every 16 months. Beyond spotlighting top-performing AI models, OpenAI says that publicly measuring efficiency -- which here refers to reducing the compute needed to train a model to perform a specific capability -- will paint a quantitative picture of algorithmic progress. It's OpenAI's assertion that this in turn will inform policy making by renewing the focus on AI's technical attributes and societal impact. "Algorithmic improvement is a key factor driving the advance of AI. It's important to search for measures that shed light on overall algorithmic progress, even though it's harder than measuring such trends in compute," OpenAI wrote in a blog post.

Is Artificial Intelligence (AI) here to stay? Will it bring a complete end to human interventions? Such questions set the context in which people generally think about AI. Whether they have come to a conclusion or not is a different matter altogether. But it can't be denied that today, AI is integral to various organizations' growth.

When it comes to job hunting, there is no other place than the largest professional and employment-oriented service platform LinkedIn. With hosting over 20 million active job postings, the largest hiring marketplace has been continuously developing its platform with the help of using intelligent models to optimise various processes such as job postings, job recommendations, handling abusive contents and much more. To the latest, the developers at LinkedIn recently unveiled a new deep learning model known as Job2Questions. Using it, recruiters can ask screening questions online to filter qualified candidates easily. The professional social networking platform has many conventional on-demand services and state-of-the-art machine learning models that help millennials and professionals in the global workforce. The developers stated that the primary goal is to match jobs with qualified applicants and improve hiring efficiency while reducing the requirement of manually screening each applicant.

Here are the most tweeted papers that were uploaded onto arXiv during April 2020. Results are powered by Arxiv Sanity Preserver. Abstract: Manga is a world popular comic form originated in Japan, which typically employs black-and-white stroke lines and geometric exaggeration to describe humans' appearances, poses, and actions. In this paper, we propose MangaGAN, the first method based on Generative Adversarial Network (GAN) for unpaired photo-to-manga translation. Inspired by how experienced manga artists draw manga, MangaGAN generates the geometric features of manga face by a designed GAN model and delicately translates each facial region into the manga domain by a tailored multi-GANs architecture.

Symbolic AI algorithms have played an important role in AI's history, but they face challenges in learning on their own. After IBM Watson used symbolic reasoning to beat Brad Rutter and Ken Jennings at Jeopardy in 2011, the technology has been eclipsed by neural networks trained by deep learning. The power of neural networks is that they help automate the process of generating models of the world. This has led to several significant milestones in artificial intelligence, giving rise to deep learning models that, for example, could beat humans in progressively complex games, including Go and StarCraft. But it can be challenging to reuse these deep learning models or extend them to new domains.

This article demonstrates how building a smarter API serving Deep Learning models minimizes the response time. Your team worked hard to build a Deep Learning model for a given task (let's say: detecting bought products in a store thanks to Computer Vision). You then developed and deployed an API that integrates this model (let's keep our example: self-checkout machines would call this API). The new product is working well and you feel like all the work is done. But since the manager decided to install more self-checkout machines (I really like this example), users have started to complain about the huge latency that occurs each time they are scanning a product. Ask data scientists to try reducing the depth of the model without degrading its accuracy?

One evening last October, the artificial intelligence researcher Gary Marcus was amusing himself on his iPhone by making a state-of-the-art neural network look stupid. Marcus' target, a deep learning network called GPT-2, had recently become famous for its uncanny ability to generate plausible-sounding English prose with just a sentence or two of prompting. When journalists at The Guardian fed it text from a report on Brexit, GPT-2 wrote entire newspaper-style paragraphs, complete with convincing political and geographic references. Marcus, a prominent critic of AI hype, gave the neural network a pop quiz. Surely a system smart enough to contribute to The New Yorker would have no trouble completing the sentence with the obvious word, "fire."