AI Technology & Industry Review
In the new paper A Generalist Neural Algorithmic Learner, a research team from DeepMind, University of Oxford, IDSIA, Mila, and Purdue University presents a novel generalist neural algorithmic learner — a single graph neural network (GNN) capable of solving various classical algorithms at single-task expert level.
DeepMind researchers present a precise and compact overview of transformer architectures and formal algorithms in the new paper Formal Algorithms for Transformers.
A research team from Google Research and Northwestern University presents polynomial time and sample-efficient algorithms for learning an unknown depth-2 feedforward neural network with general ReLU activations, aiming to provide insights into whether efficient algorithms exist for learning ReLU networks.
A research team from DeepMind explores how neural networks can be fused with algorithmic computation and demonstrates an elegant neural end-to-end pipeline that goes straight from raw inputs to general outputs while emulating an algorithm internally.
On August 28, China’s Ministry of Commerce and Ministry of Science and Technology released the new updated version of the Catalogue of Technologies Prohibited and Restricted from Export.
Researchers proposed an optimized deep learning algorithm for detecting sensory events occurring during stimulation of the nerves using a stretchable and flexible electrocorticography (ECoG) electrode.
Google researchers propose an “AutoML-Zero” approach designed to automatically search for machine learning (ML) algorithms from scratch, requiring minimal human expertise or input.
LinearDesign, an efficient algorithm for optimized mRNA sequence design.
Researchers have introduced a novel hybrid continual learning algorithm, Adversarial Continual Learning, which aims to enable the persistent explicit or implicit replay of experiences by storing original samples
The tool can significantly accelerate the prediction time of a virus’s RNA secondary structure, affording frontline researchers an opportunity to better understand the virus and develop targeting vaccines in a time of crisis.
A new paper from the University of Washington Seattle and the University of California, Berkeley looks at saddle points on Riemannian Manifolds. In this article Synced takes a deep dive into this important research.
To help users design and tune machine learning models, neural network architectures or complex system parameters in an efficient and automatic way, in 2017 Microsoft Research began developing its Neural Network Intelligence (NNI) AutoML toolkit, open-sourcing v1.0 version in 2018.
Facebook AI Research team has introduced a new “point-based rendering” neural network module with an iterative subdivision algorithm that can integrate SOTA image segmentation models.
A team of researchers from the University of California at Berkeley, ETH, Zhejiang University, and the University of Illinois at Urbana-Champaign set out to put a price on data in the context of machine learning in their 2019 research papers.
Pryzant and other Stanford researchers partnered with researchers from Kyoto University and Georgia Institute of Technology to develop a novel natural language model that can identify and neutralize biased framings, presuppositions, attitudes, etc. in text.
What if an AI could learn to play Chess based only on human game commentary? That interesting task has been tackled by SentiMATE, a new Chess algorithm proposed by University College London.
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.
Model-free reinforcement learning can be used to learn effective strategies for complex tasks such as Atari games, but it usually requires a large amount of interaction, which adds significant time and cost.
A paper recently accepted for ICLR 2019 challenges this with a novel optimizer — AdaBound — that authors say can train machine learning models “as fast as Adam and as good as SGD.” Basically, AdaBound is an Adam variant that employs dynamic bounds on learning rates to achieve a gradual and smooth transition to SGD.
Researchers from Beijing-based AI unicorn SenseTime and Nanyang Technological University have trained ImageNet/AlexNet in a record-breaking 1.5 minutes, a significant 2.6 times speedup over the previous record of 4 minutes.
While previous pregnancy detection techniques relied heavily on human labour, Alibaba’s new “pregnancy diagnosis algorithms” can help. The AI system was developed by Alibaba Cloud engineers in a joint effort with pig farming scientists.
Alibaba has announced it will open-source X-Deep Learning (XDL), the algorithm framework behind its marketing technology and big data platform Alimama. The source code and support documents’ release is slated for December.
This paper proposes a learning algorithm to speed up search in Task and Motion Planning problems (TAMP), and to solve three challenges in order to improve planning efficiency.
In order to deploy Recurrent Neural Networks (RNNs) efficiently, we propose a technique to reduce the parameters of a network by pruning weights during the initial training of the network.
Intelligent behavior arises from the actions of an individual seeking to maximize its received reward signals in a complex and changing world”. Meanwhile, reinforcement learning is the way to realize AI.
TensorFlow is one of the most popular open source AI libraries. Its high in computing efficiency, and the rich development resources make it widely adopted by companies and individual developers.
Thanks to AlphaGo, the term “Artificial Intelligence” (AI) came under the spotlight (again). However, Jean-Christophe Baillie doesn’t agree that AlphaGo is AI, for the reason that it’s not able to get us to full AI – an Artificial General Intelligence (AGI).
This paper proposes an adaptive learning rate algorithm, which utilizes stochastic curvature information of the loss function for automatically tuning the learning rates.