AI Technology & Industry Review
Twitter Chief Scientist Michael Bronstein, Joan Bruna from New York University, Taco Cohen from Qualcomm AI and Petar Veličković from DeepMind publish a paper that aims to geometrically unify the typical architectures of CNNs, GNNs, LSTMs, Transformers, etc. from the perspective of symmetry and invariance to build an “Erlangen Programme” for deep neural networks.
Researchers from Carnegie Mellon University, the University of Texas at Austin and Facebook AI propose a novel paradigm to optimize widths for each CNN layer. The method is compatible across various width optimization algorithms and networks and achieves up to a 320x reduction in width optimization overhead without compromising top-1 accuracy on ImageNet.
A research team from ETH and UC Berkeley proposes a Deep Reward Learning by Simulating the Past (Deep RLSP) algorithm that represents rewards directly as a linear combination of features learned through self-supervised representation learning and enables agents to simulate human actions backwards in time to infer what they must have done.
A research team from Technical University of Munich, Google, Nvidia and LMU München proposes CodeTrans, an encoder-decoder transformer model which achieves state-of-the-art performance on six tasks in the software engineering domain, including Code Documentation Generation, Source Code Summarization, Code Comment Generation, etc.
A team from Qualcomm AI proposes the direct mapping of a deep neural network onto an optical quantum computer through the language of quantum field theory, paving the way for the future development of novel quantum neural network architectures.
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 research team from Google and Johns Hopkins University identifies variance-limited and resolution-limited scaling behaviours for dataset and model size in four scaling regimes.
The research develop machine learning methods that enable virtual agents (such as avatars from a computer game) to communicate non-verbally.
Researchers from Drexel University, Northeastern University and IT University Copenhagen explore how humans interact with AI in such contexts, with a focus on computer games.
In a new paper, Stanford University researchers dispel the assumption that boosting deep learning model performance on ImageNet translates to better performance on medical imaging tasks.
Synced invited Dr. Linchao Zhu, a lecturer at the ReLER lab, University of Technology Sydney whose works focus on video representation learning, to share his thoughts on the paper Text-to-Image Generation Grounded by Fine-Grained User Attention.
On January 18, in efforts to understand and manage extreme weather events, McGill University announced a new interdisciplinary project to combine deep learning (DL) with social network analysis (SNA).
Porsche Digital, the subsidiary of the Stuttgart-based sports car manufacturer, has unveiled digital assistant ‘Sounce’ offers an improved ability to detect noise – for example, during vehicle component tests.
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.
Looking back at the evolution of deep learning frameworks we can clearly see a tightly coupled relationship between deep learning frameworks and deep learning algorithms.
CSAIL researchers propose a framework for image reconstruction tasks using the state-of-the-art generative model StyleGAN2.
A research team from Asan Medical Center (AMC) in Seoul has verified a deep learning-based algorithm for detecting up to 43 types of skin cancer and diseases.
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 Expert Roadmap developed by German software company AMAI is garnering keen interest from aspiring AI professionals around the world.
An international research team is suggesting AI might become even more efficient and reliable if it learns to think more like worms.
“The Computational Limits of Deep Learning” first author Neil Thompson of MIT says DL’s economic and environmental footprints are growing worrying fast
Pinkney and Adler NeurIPS 2020 workshop paper enables realistic image generation in domains such as animation and ukiyo-e with creative control on the output.
Google Brain recently introduced a new open-sourced TensorFlow package, TensorFlow Recommenders designed to simplify the process of building, evaluating, and serving sophisticated recommender models.
UIUC, Adobe Research and University of Oregon propose HDMatt, a Deep Learning-based image matting Cross-Patch Context module for high-resolution image inputs.
Microsoft has released four additional DeepSpeed technologies to enable even faster training times, whether on supercomputers or a single GPU.
Preferred Networks announced that PFN and Mitsui established a new joint venture Mit-PFN Energy to develop and commercialize a deep learning-based AI solution for subsurface structure analysis.
The 16th European Conference on Computer Vision (ECCV) kicked off on Sunday as a fully online conference. In the Conference Opening Session this morning, the ECCV organizing committee announced the conference’s paper submission stats and Best Paper selections.
Researchers introduced an ensemble-based deep learning pipeline to automatically assess the distal radius and ulna (DRU) maturity from left-hand radiographs.
PFRL succeeds ChainerRL as comprehensive library with cutting-edge deep reinforcement learning algorithms and features.
Fujitsu has developed the world’s first AI technology that accurately captures the characteristics of high-dimensional data without labeled training data.
Researchers developed a novel deep learning method that reconstructs PET images using a cascading back-projection neural network (bpNet).
A team of researchers proposed a novel three-stage learning framework that includes scene context to generate long-term 3D human motion prediction when given a single scene image and 2D pose histories.
Researchers introduce a novel Physical Scene Graphs (PSG) approach designed to obtain a better structured understanding of visual scenes.
A team of researchers from Princeton, DeepMind and New York University have introduced a new method that extracts symbolic representations from deep learning models by introducing strong induction biases.
Neuropod, an open-source library that provides a uniform interface for running deep learning (DL) models from multiple frameworks in C++ and Python.
A team of researchers from the Chinese Academy of Sciences and the City University of Hong Kong has introduced a local-to-global approach that can generate lifelike human portraits from relatively rudimentary sketches.
Facebook this week released Detection Transformers (DETR), a new approach for object detection and panoptic segmentation tasks that uses a completely different architecture than previous object detection systems.
Paddle Quantum is developed based on Baidu’s deep learning platform PaddlePaddle, which has become the first and unique deep learning platform in China that supports quantum machine learning.
Recent advances in deep learning, also known as using neural machine learning, has proven to achieve state of the art results in machine translation.
The proposed method outperforms supervised methods and unsupervised translation methods on restoring real photos.