AI Technology & Industry Review
A research team from UC Berkeley and Carnegie Mellon University proposes a task-agnostic reinforcement learning method that reduces the task-specific engineering required for domain randomization of both visual and dynamics parameters.
A research team from NVIDIA, Stanford University and Microsoft Research propose a novel pipeline parallelism approach that improves throughput by more than 10 percent with a comparable memory footprint, showing such strategies can achieve high aggregate throughput while training models with up to a trillion parameters.
A team from Mila, University of Montreal, DeepMind, Waverly and Google Brain proposes Neural Production Systems, which serve to factorize entity-specific and rule-based information in rich visual environments.
A team from Google Research explores why most transformer modifications have not transferred across implementation and applications, and surprisingly discovers that most modifications do not meaningfully improve performance.
A research team lead by Geoffrey Hinton has created an imaginary vision system called GLOM that enables neural networks with fixed architecture to parse an image into a part-whole hierarchy with different structures for each image.
Stanford researchers’ DERL (Deep Evolutionary Reinforcement Learning) is a novel computational framework that enables AI agents to evolve morphologies and learn challenging locomotion and manipulation tasks in complex environments using only low level egocentric sensory information.
A new study by the Georgia Institute of Technology and Facebook AI introduces TT-Rec, a way to drastically compress the size of memory-intensive Deep Learning Recommendation Models (DLRM) and make them easier to deploy at scale.
Researchers from Naver AI Lab says they’ve found a computationally efficient re-labelling strategy that fixes a significant flaw in popular image classification benchmark ImageNet.
A paper in the Journal of Artificial Intelligence Research goes a step further, warning that it could become fundamentally impossible to control a superintelligent AI.
Google Brain’s Switch Transformer language model packs a whopping 1.6 trillion parameters while effectively controlling computational cost. The model achieved a 4x pretraining speedup over a strongly tuned T5-XXL baseline.
Of the 2997 submissions, 860 papers have made it to ICLR 2021, for an acceptance rate of 28.7 percent — slightly higher than last year’s 26.5 percent.
OpenAI has trained a neural network called DALL·E that creates images from text captions for a wide range of concepts expressible in natural language.
This is the fourth Synced year-end compilation of “Artificial Intelligence Failures.” Our aim is not to shame nor downplay AI research, but to look at where and how it has gone awry with the hope that we can create better AI systems in the future.
As part of our year-end series, Synced has compiled a global list of proposals, rules and regulatory frameworks for AI introduced in 2020.
As part of our year-end series, Synced highlights 10 AI-powered efforts that contributed to the fight against COVID-19 in 2020.
Synced has compiled a list of nonfiction books that notable AI researchers and engineers have recommended on Twitter over the last 12 months.
As part of our year-end series, Synced highlights 10 AI-powered art projects that inspired and entertained us in 2020.
Synced has selected 10 AI-related podcasts for readers to check out over the holiday season.
Researchers combine the effectiveness of the inductive bias in CNNs with the expressivity of transformers to model and synthesize high resolution images.
In the new paper Canonical Capsules: Unsupervised Capsules in Canonical Pose, Turing Award Honoree Dr. Geoffrey Hinton and a team of researchers propose an architecture for unsupervised learning with 3D point clouds based on capsules.
As part of our year-end series, Synced highlights 10 artificial intelligence papers that garnered extraordinary attention and accolades in 2020.
This year, 22 Transformer-related research papers were accepted by NeurIPS, the world’s most prestigious machine learning conference. Synced has selected ten of these works to showcase the latest Transformer trends.
Yoshua Bengio and Anirudh Goyal from Mila - Quebec AI Institute delve into human and non-human animal intelligence and how it can inform deep learning.
“Depix” is a new AI-powered tool that can easily undo pixelization to enable recovery of the information therein.
The new AI-powered Multi-Ingredient Pizza Generator (MPG) can deliver all these mouth-watering pies and many more.
ImHex’s creator says his trending hex editor is aimed at “Reverse Engineers, Programmers and people that value their eyesight when working at 3 AM.”
Google DeepMind has added Jraph to the JAX ecosystem, the machine learning framework will also appear in a NeurIPS 2020 Spotlight.
OpenAI’s groundbreaking GPT-3 language model paper, a no-regret learning dynamics study from Politecnico di Milano & Carnegie Mellon University, and a UC Berkeley work on data summarization have been named the NeurIPS 2020 Best Paper Award winners.
AAAI 2021 received a record-high 9034 submissions and over 7911 papers went to review and a total of 1692 papers made it, for an acceptance rate of 21 percent
The approach dramatically reduces bandwidth requirements by sending only a keypoint representation [of faces] and reconstructing the source video on the receiver side with the help of generative adversarial networks (GANs) to synthesize the talking heads.
A Princeton student designed a GAN framework for Chinese landscape painting generation that is so effective most humans can’t distinguish its works from the real thing.
Google’s UK-based lab and research company DeepMind says its AlphaFold AI system has solved the protein folding problem, a grand challenge that has vexed the biology research community for half a century.
Researchers from the City University of Hong Kong and SenseTime propose a lightweight matting objective decomposition network (MODNet) that can smoothly process real-time human matting from a single input image with diverse and dynamic backgrounds.
University of Alberta recently proposed U^2-Net, a novel deep network architecture that achieves very competitive performance in salient object detection.
A new AI-powered image synthesis framework makes “learning” to moonwalk or drop Blackpink dance moves a snap.
Facebook AI is building an automatic differentiation system for the Kotlin programming language and developing a system for tensor typing.
The Conference on Empirical Methods in Natural Language Processing (EMNLP 2020) kicked off on Monday as a virtual conference.
A new DeepMind scalable environment simulator takes a digital approach to the question, enabling the examination of environmental factors on AI agents.
Google Research and DeepMind debut Long-Range Arena (LRA) benchmark for Transformer research on tasks with long sequence lengths.
Google Brain ICLR 2021 submission analyzes learned optimizers’ performance advantage over well-tuned baseline optimizers.