AI Technology & Industry Review
Technical review of the newest machine intelligence research.
Leading UK AI research company DeepMind has now proposed “BigBiGAN” (not BigBigGAN, but BigBiGAN), which achieves state-of-the-art results in both unsupervised representation learning on ImageNet and in unconditional image generation.
If you are a developer who has ever wished for a rich collection of machine learning algorithms implemented exclusively in NumPy, then you’ll love Numpy-ml — a new GitHub project that’s winning accolades from across the global machine learning community.
A group of researchers from the Chinese University of Hong Kong, Harbin Institute of Technology and Tencent have proposed a method to create such cartoon faces from photos of human faces via a novel CycleGAN model informed by facial landmarks.
In common reinforcement learning (RL) domains, existing keypoint discovery methods struggle to perceive keypoints in an image when there are limited objects present.
MIT and Brown have now upgraded the Northstar platform with an AutoML-based component called Virtual Data Scientist (VDS), which helps users generate machine learning models to run prediction tasks on datasets.
Facebook published a blog article demonstrating their newly developed code search tool, Neural Code Search (NCS).
Parsing fine-grained temporal actions is vital in application scenarios that require an understanding of detailed and precise operations over long-term periods, such as daily activity understanding, surgical robots, human motion analysis and animal behavior analysis.
While it is exhilarating to see AI researchers pushing the performance of cutting-edge models to new heights, the costs of such processes are also rising at a dizzying rate.
In 2017 the “Godfather of Deep Learning” Geoffrey Hinton and his students Sara Sabour and Nicholas Frosst proposed the discrimininatively trained, multi-layer capsule system “CapsNet” in their paper Dynamic Routing Between Capsules.
Facebook AI research team show how they trained a large convolutional network to predict hashtags on some 3.5 billion social media images. The research returned a state-of-the-art top-1 accuracy result of 85.4 percent on ImageNet.
Researchers from Microsoft and JD AI Labs have proposed Object-driven Attentive Generative Adversarial Networks (Obj-GAN) a new model capable of generating relatively complex scenes based on a short phrase or sentence of descriptive text.
A team of researchers from Carnegie Mellon University and Google Brain have now proposed XLNet, a new language model which outperforms BERT on 20 language tasks including SQuAD, GLUE, and RACE; and has achieved SOTA results on 18 of these tasks.
Citadel Chief AI Officer Li Deng has been named a Fellow of the Canadian Academy of Engineering (CAE) in recognition of his notable achievements in deep learning and speech recognition.
acebook’s AI’s new “Inverse Cooking” AI system reverse-engineers recipes from food images, predicting both the ingredients in the dish and their preparation and cooking instructions.
In an unprecedented “call for collaboration,” a group of 22 respected AI experts that includes Andrew Ng, Yoshua Bengio, and Demis Hassabis have published a paper exploring how machine learning (ML) could help deal with climate change by reducing greenhouse gases (GHG).
Many cat owners have awoken to the sound of frenzied scrambling across the floor as their furry feline friend chases the mouse it snuck into the house in the middle of the night. Or looked up to find their pet staring down with those adorable big round eyes at the dead little fledgling it has deposited beside your pillow as a “present.“
Researchers from New York University and Facebook AI Research recently added 50,000 test samples to the dataset. Facebook Chief AI Scientist Yann LeCun, who co-developed the MNIST, tweeted his approval: “MNIST reborn, restored and expanded.”
The 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) kicked off today in Long Beach, California. CVPR is one of the world’s top three academic conferences in the field of computer vision (along with ICCV and ECCV).
Microsoft has updated the performance of their Multi-Task Deep Neural Network (MT-DNN) ensemble model. The significant performance boost has the model sitting comfortably atop the benchmark GLUE rankings, as shown in the following table.
Deep learning model performance has taken huge strides, allowing researchers to tackle tasks which were simply not possible for machines less than a decade ago.
In a joint effort with the Perimeter Institute for Theoretical Physics and Alphabet (Google) X, Google AI researchers recently announced a new open source library, TensorNetwork, which can greatly improve the efficiency of tensor calculations for tensor network algorithms.
Architecture and weights are two essential considerations for artificial neural networks. Architecture is akin to the innate human brain, and contains the neural network’s initial settings such as hyperparameters, layers, node connections (or wiring), etc.
The 36th International Conference on Machine Learning (ICML) kicked off Monday in California. The ICML is one of the world’s two top conferences in ML and AI (the other being NeurIPS).
In a bid to provide a smoother reproduction experience, Facebook has announced the beta release of PyTorch Hub, a new pretrained model repository designed to facilitate research reproducibility testing.
A new paper from Google’s UK-based research company DeepMind addresses this with a model based on Contrastive Predictive Coding (CPC) that outperforms the fully-supervised AlexNet model in Top-1 and Top-5 accuracy on ImageNet.
A group of researchers from Tencent Technology, the Chinese University of Hong Kong, and Nankai University recently combined two commonly used techniques — Batch Normalization (BatchNorm) and Dropout — into an Independent Component (IC) layer inserted before each weight layer to make inputs more independent*.
Synced Global AI Weekly June 9th
A favourite is the collaborative card game Hanabi, which won the 2013 Spiel des Jahres and 2013 Fairplay À la Carte Award. The game has now drawn the attention of AI researchers.
Google today announced the release of the Beta version of TensorFlow 2.0. The new version of the world’s most popular open source machine learning library is being welcomed by developers.
Building large datasets is a time-consuming and labor-intensive task which challenges entities with limited budgets. There are hundreds of open visual datasets out there, but searching across them and their millions of entries is not a simple task.
DeepMind is a trailblazer in the trending computer vs humans gaming research space. Following milestone victories against human pros on the board game Go and video game StarCraft II, the Google-owned research company has now pitted their new AI system against humans in the first-person shooter multiplayer video game Quake III Arena.
Generative adversarial networks (GANs) have become AI researchers’ “go-to” technique for generating photo-realistic synthetic images. Now, DeepMind researchers say that there may be a better option.
Might there be a more efficient approach to scaling up CNNs to improve accuracy? Researchers from Google AI say “yes” and have proposed a new model scaling method in their ICML 2019 paper EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks.
Researchers from Technische Universität Wien, Austria, and Politecnico di Torino, Italy, explored adversarial attacks on Capsule Networks, proposing an algorithm which automatically generates targeted adversarial examples in black-box attack scenarios.
Berkeley Artificial Intelligence Research (BAIR) has introduced a new reinforcement learning (RL) method, Stochastic Optimal Control with Latent Representations (SOLAR), which can help robots quickly learn tasks such as stacking blocks or pushing objects from visual inputs.
Earlier this month restored images of iconic Hong Kong film stars like Bridget Lin and Joey Wong began circulating on Chinese social media. An AI-enabled touch-up process revealed distinct facial contours and features in old and fuzzy or low-res photos, revisiting the comely visages that made the public fall in love with these ’90s stars.
Researchers from Tsinghua University and Huawei Noah’s Ark Lab recently proposed a new model that incorporates knowledge graphs (KG) into training on large-scale corpora for language representation.
Compressed Sensing’s ability to exploit the structure of natural images and recover an image from limited random measurements have made it an elegant framework for recovering sparse signals from compressed measurements.
A Google Brain research team led by Turing Award recipient Geoffrey Hinton recently published a paper that presents an effective method for measuring the similarity of representations learned by deep neural networks.
Synced Global AI Weekly May 26th