AI Technology & Industry Review
A research team from Google and the University of California, Berkeley calculates the energy use and carbon footprint of large-scale models T5, Meena, GShard, Switch Transformer and GPT-3, and identifies methods and publication guidelines that could help reduce their CO2e footprint.
A research team from McGill University, Mila – Quebec AI Institute and Facebook AI proposes novel metrics and perturbation functions to detect, quantify and compare trade-offs between robustness and faithfulness in NMT systems, both on the corpus level and with particular examples.
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 Rice University, IBM and USC combine compressed sensing, non-convex optimization and acceleration techniques to introduce a new algorithm — Momentum Inspired Factored Gradient Descent (MiFGD) — that pushes QST beyond current capabilities.
A research team from DeepMind introduces Anakin and Sebulba, two architectures that demonstrate reinforcement learning platforms based on TPUs can efficiently deliver exceptional performance at scale and with low cost.
A research team from ETH Zurich leverages existing spike-based learning circuits to propose a biologically plausible architecture that is highly successful in classifying distinct and complex spatio-temporal spike patterns. The work contributes to the design of ultra-low-power mixed-signal neuromorphic processing systems capable of distinguishing spatio-temporal patterns in spiking activity.
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 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 Google Brain and New York University says the Natural Language Understanding (NLU) evaluation system is “broken” and proposes four criteria for improving NLU benchmarks.
A research team from IBM introduces two systems for predicting information type: The TypeSuggest module, an unsupervised system designed to generate types for a set of seed query terms input by the user; and an Answer Type prediction module for predicting the correct answer type for user-provided questions.
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 research team from University of Washington, Microsoft, DeepMind and Allen Institute for AI develop a method to convert pretrained transformers into efficient RNNs. The Transformer-to-RNN (T2R) approach speeds up generation and reduces memory cost.
A team from University of Michigan, MIT-IBM Watson AI Lab and ShanghaiTech University publishes two papers on individual fairness for ML models, introducing a scale-free and interpretable statistically principled approach for assessing individual fairness and a method for enforcing individual fairness in gradient boosting suitable for non-smooth ML models.
A research team from Princeton University and Microsoft Research discover autonomous language-understanding agents are capable of achieving high scores even in the complete absence of language semantics, indicating that current RL agents for text-based games might not be sufficiently leveraging the semantic structure of game texts.
A research team from DeepMind and Alberta University proposes Policy-guided Heuristic Search (PHS), a novel search algorithm that uses both a heuristic function and a policy while offering guarantees on the search loss that relate to both the quality of the heuristic and the policy.
The Beijing Academy of Artificial Intelligence (BAAI) releases Wu Dao 1.0, China’s first large-scale pretraining model.
A research team from DeepMind proposes manipulation-independent representations (MIR) that can support successful imitation of behaviours demonstrated by previously unseen manipulator morphologies using only visual observations.
Researchers from Google, Georgia Tech and Emory University examine the semantic changes in abolitionist newspapers and explore whether the papers exhibited leadership or were followers, providing an overall picture of their network of semantic influence.
A research team from Hugging Face shows that prompting is indeed beneficial for fine-tuning pretrained language models, and that this benefit can be quantified as worth hundreds of data points on average across classification tasks.
A Facebook AI research team explores strategies for convolutional neural network scaling, aiming to provide a framework for analyzing scaling strategies under various computational constraints.
University of Oxford researchers propose COIN, a novel image compression method that stores the weights of an MLP overfitted to an image and outperforms JPEG at low bitrates even without entropy coding.
A research team from Facebook AI proposes a Contrastive Semi-supervised Learning (CSL) approach that synthesizes pseudo-labelling and contrastive losses to improve the stability of learned speech representations for automatic speech recognition (ASR).
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 research team from Google and EPFL proposes a novel approach that sheds light on the operation and inductive biases of self-attention networks, and finds that pure attention decays in rank doubly exponentially with respect to depth.
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 Facebook and Google has proposed LazyTensor — a technique for targeting domain-specific compilers without sacrificing define-by-run ergonomics.
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 team from Max-Planck Institute for Intelligent Systems, ETH Zurich, Google Research Amsterdam, Mila and the University of Montreal make an effort to bring together causality and machine learning research programs, delineate implications of causality for machine learning and propose critical areas for future research.
Google AI created Lyra, a high-quality, very low-bitrate speech codec that makes voice communication available even on the slowest networks.
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.
A research team from Facebook AI has proposed a Unified Transformer (UniT) encoder-decoder model that jointly trains on multiple tasks across different modalities and achieves strong performance on seven tasks with a unified set of model parameters.
A team from Microsoft and Université de Montréal proposes a new mathematical framework that uses measure theory and integral operators to achieve the goal of quantifying the regularity of the attention operation.
A research team from UC Berkeley, University of Maryland and UC Irvine identifies pitfalls that cause instability in the GPT-3 language model and proposes a contextual calibration procedure that improves accuracy by up to 30 percent.
A Microsoft team has introduced Error Analysis, a responsible AI toolkit designed to identify and diagnose errors in machine learning models.
University of Toronto researchers propose a BERT-inspired training approach as a self-supervised pretraining step to enable deep neural networks to leverage newly and publicly available massive EEG (electroencephalography) datasets for downstream brain-computer-interface (BCI) applications.
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.
DeepMind has designed a family of Normalizer-Free ResNets (NFNets) that can be trained in larger batch sizes and stronger data augmentations and have set new SOTA validation accuracies on ImageNet.
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.
The research develop machine learning methods that enable virtual agents (such as avatars from a computer game) to communicate non-verbally.
Researchers from the University of Sheffield, Beihang University, and Open University’s Knowledge Media Institute have proposed a transfer learning approach that can automatically process historical texts at a semantic level to generate modern language summaries.