Researchers from Facebook, the National University of Singapore, and the Qihoo 360 AI Institute have jointly proposed OctConv (Octave Convolution), a promising new alternative to traditional convolution operations. Akin to a “compressor” for Convolutional Neural Networks (CNN), the OctConv method saves computational resources while boosting effectiveness.
As robots take over industrial manufacturing, specific and accurate robot control is becoming more important. Conventional feedback control methods can effectively solve various types of robot control problems by capturing structures with explicit models such as motion equations.
Facebook AI Research has announced it is open-sourcing PyTorch-BigGraph (PBG), a tool that can easily process and produce graph embeddings for extremely large graphs. PBG can also process multi-relation graph embeddings where a model is too large to fit in memory.
Now, China’s elite Central Conservatory of Music (CCOM) has announced it is recruiting PhDs for a new Music AI and Information Technology program. CCOM says prospective students should have a background in Computer Science, AI, or Information Technology; along with musical abilities (instrument playing or singing).
Google Brain researchers have proposed LAMB (Layer-wise Adaptive Moments optimizer for Batch training), a new optimizer which reduces training time for its NLP training model BERT (Bidirectional Encoder Representations from Transformers) from three days to just 76 minutes.
In a scene that looks like it’s from a sci-fi movie, a YouTube video posted today by robotics company Boston Dynamics shows a huge, ostrich-like robot “Handle” whirling round while deftly moving boxes in a warehouse. The video has garnered over 138,000 views in less than four hours.
NVIDIA CEO and Co-Founder Jensen Huang says a rumored next-generation GPU architecture is not a priority for the company, and that he remains optimistic about clearing the chip inventory built up for cryptocurrency mining. Huang made the remarks in a press conference Tuesday at the GPU Technology Conference (GTC) in Santa Clara.
It is no secret that deep neural networks (DNNs) can achieve state-of-the-art performance in a wide range of complicated tasks. DNN models such as BigGAN, BERT, and GPT 2.0 have proved the high potential of deep learning. Deploying DNNs on mobile devices, consumer devices, drones and vehicles however remains a bottleneck for researchers.
DeepMind’s Research Platform Team has open-sourced TF-Replicator, a framework that enables researchers without previous experience with the distributed system to deploy their TensorFlow models on GPUs and Cloud TPUs. The move aims to strengthen AI research and development.
NVIDIA’s annual GPU Technology Conference (GTC) attracted some 9,000 developers, buyers and innovators to San Jose, California this week. CEO and Co-Founder Jensen Huang’s two-and-a-half hour keynote speech fused GPU-based innovations in domains ranging from graphic design to autonomous driving.
A new GitHub project, PyTorch Geometric (PyG), is attracting attention across the machine learning community. PyG is a geometric deep learning extension library for PyTorch dedicated to processing irregularly structured input data such as graphs, point clouds, and manifolds.
The University of California has halted all further subscriptions with one of the world’s largest scholarly publishers, Amsterdam-based Elsevier. The move follows more than six months of negotiations which failed to reach a substantial agreement on securing universal open access to UC research.
TensorFlow is the world’s most popular open source machine learning library. Since its initial release in 2015, the Google Brain product has been downloaded over 41 million times. At this week’s 2019 TensorFlow Dev Summit, Google announced a major upgrade on the framework, the TensorFlow 2.0 Alpha version.
Machine learning models based on deep neural networks have achieved unprecedented performance on many tasks. These models are generally considered to be complex systems and difficult to analyze theoretically. Also, since it’s usually a high-dimensional non-convex loss surface which governs the optimization process, it is very challenging to describe the gradient-based dynamics of these models during training.
The Conference on Computer Vision and Pattern Recognition (CVPR) announced this week they have accepted 1300 research papers for CVPR 2019, which will be held June 16 – 20 in Long Beach, California. This year’s submission and acceptance totals both set records for the world’s premier computer vision conference, which had never before accepted more than 1000 papers.
Having notched impressive victories over human professionals in Go, Atari Games, and most recently StarCraft 2 — Google’s DeepMind team has now turned its formidable research efforts to soccer. In a paper released last week, the UK AI company demonstrates a novel machine learning method that trains a team of AI agents to play a simulated version of “the beautiful game.”
Facebook AI Chief Yann LeCun introduced his now-famous “cake analogy” at NIPS 2016: “If intelligence is a cake, the bulk of the cake is unsupervised learning, the icing on the cake is supervised learning, and the cherry on the cake is reinforcement learning (RL).”