首页 博客 Page 3

脸书 AI推出Linformer:一种新的变压器架构,可捕捉仇恨暴力的仇恨言论和内容

部署系统以检测充满语或故意拼写错误的仇恨言论一直是一个巨大的挑战。如今,功能最强大,最先进的语言理解系统使用具有数十亿或数万亿参数的大型Transformer模型。就像Facebook AI一样 RoBERTa and XLM-R, some new models make constant 和 repetitive advancements that are state-of-the-art, but with the help of even larger models...

脸书 AI探索Kotlin语言的自动区分系统

Differentiable programming enables programs to optimize themselves 和 is a part of 脸书 AI’s broader efforts to build additional advanced machine learning programming tools. 脸书 AI is developing an automatic differentiation system for the Kotlin programming language.  研究人员表示,这项工作将进一步探索软件2.0,在此软件可以有效地自我编写。那个...

艾伯塔大学的研究人员提出了U2- Net:一种新型的深层网络架构,该架构可通过显着物体检测生成逼真的铅笔肖像

In the computer vision field, the process of detection 和 segmentation of the most noticeable objects from natural scenes is known as salient object detection (SOD).  Most of the existing SOD networks have similar designs 和 leverage the depth features extracted by backbone networks like AlexNet, ResNet, ResNeXt, DenseNet, VGG, etc. These backbone networks...

加州大学伯克利分校的研究人员将AI用于静音语音的数字发声

Researchers at 加州大学伯克利分校 have developed an AI model that detects ‘silent speech.’ The model is based on digital voicing to predict words 和 generate synthetic speech. Electromyography (EMG), with electrodes located at the face 和 throat, is used to detect the silent speech. 研究人员断言,该模型可以为...提供许多应用程序。

探索量子机器学习中数据的力量

量子计算机具有开发能力 量子机器学习 算法。这些算法可以为建模分子,催化剂或高温超导体等量子力学系统提供更好的性能。由于经典计算机很难处理量子世界中指数演化态的干扰,因此量子计算机有望在量子起源机器中占有优势。

艾伦AI研究所推出TL; DR:一种能够一口气总结研究论文的AI工具

艾伦人工智能研究所(AI2)的研究人员开发了一种新的AI模型,该模型可以汇总科学论文中的文字。当用户使用搜索功能或进入作者页面时,它提供句子形式TL; DR(未读太久)摘要。 团队已将此模型推广到...

谷歌’s Latest AI Tool, 奇美拉画家, Uses Machine Learning To Create Fantastical Creatures

Google的研究人员开发了一种新的AI工具,名为 Chimera Painter that turns doodles into unusual creatures. This tool uses machine learning to create representation based on the user’s rough sketches. Before this, Nvidia has used a similar concept with landscapes, 和 麻省理工学院 和 IBM公司 have produced a similar idea with buildings.  A high level...

程式化的神经画家:一种图像到绘画的翻译方法,可以生成样式可控的生动逼真的绘画作品

Researchers from the 密西根大学, NetEase Fuxi AI Lab, 和 Beihang University in China recently introduced Stylized Neural Painter. Stylized Neural Painter is a novel automatic tool that can generate vivid 和 realistic artwork in controllable styles from images. Stylized Neural Painter works on generative modeling, image translation, 和 style transfer methods with strong neural networks.

利用ML计算框架在Mac上提高TensorFlow性能

TensorFlow 2 offers best-in-class training performance on various platforms, devices, 和 hardware. This empowers researchers 和 professionals to work on their favored platform. TensorFlow users on 英特尔 Macs or Macs powered by 苹果’s new M1 chip can now benefit from accelerated training using 苹果’s Mac的TensorFlow 2.4优化版本 以及新的机器学习(ML)计算框架。张量的能力...

谷歌 AI发布‘Hum to 搜索’:一种新的机器学习系统,可帮助通过哼唱找到歌曲

Google最近推出了 Hum to 搜索,这是Google 搜索中一种新的机器学习的系统,可通过哼唱帮助查找歌曲。这种方法可直接从歌曲的频谱图中嵌入旋律,而无需创建中间表示。这样一来,模型就可以在没有MIDI(乐器...
Join the AI conversation 和 receive newsletters, offers & invitations.