Applying Linearly Scalable Transformers to Model Longer Protein Sequences
Researchers proposed a new transformer architecture called “Performer” — based on what they call fast attention via orthogonal random features (FAVOR).
Advertisements
Tag: Machine Learning
MLPerf Training v0.7 Results Released: Google & NVIDIA Lead the Race
The industry-standard MLPerf benchmark today released the results of the third round of its ongoing ML Training Systems competition.
Google Proposes Lasso Algorithm Variant for Learning Convolutions: ‘Bridging the Gap Between Fully-Connected and Convolutional Nets’
Unlike previous work that suggested fully-connected networks can only deliver subpar performance, Neyshabur’s experiments showed a significant performance jump.
New White-Box Framework Will Cartoonize Your World
This framework can generate high-quality cartoonized images with much-improved controllability.
Adobe and Stanford Unveil SOTA Method for Human Pose Estimation
The researchers say the approach produces motions that are visually and physically much more plausible than state-of-the-art methods.
DeepMind’s AlignNet Learns Stable Object Representations Across Time
New research from UK based AI company and research lab DeepMind is enabling AI agents to perceive dynamic real-world environments more like humans do.
Microsoft & MIT Apply Adversarially Robust Models for Better Transfer Learning
Despite being less accurate on ImageNet, adversarially robust neural networks can match or improve their standard counterparts’ transfer performance.
Joint Spatial-Temporal Transformation Learning Boosts Video Inpainting Performance
Researchers introduce a joint Spatial-Temporal Transformer Network (STTN) to tackle such video inpainting challenges.
Facebook & Inria Propose High-Performance Self-Supervised Technique for CV Tasks
Researchers have developed a new technique for self-supervised training of convolutional networks used for image classification and other computer vision tasks.
Automating Machine Learning: Google AutoML-Zero Evolves ML Algorithms From Scratch
Google researchers propose an “AutoML-Zero” approach designed to automatically search for machine learning (ML) algorithms from scratch, requiring minimal human expertise or input.
Grounded Language Learning: A Look at the Paper ‘Understanding Early Word Learning in Situated Artificial Agents’
This paper carefully engineers artificial-language learning experiments to replicate sources of information infants learn from and under what conditions.
NVIDIA Novel vid2vid Framework Synthesizes Realistic World-Consistent Videos
NVIDIA researchers propose a novel vid2vid framework that utilizes all past generated frames during rendering.
Popular Microsoft Chatbot XiaoIce Gains Independence as a New Company Led by Di Li and Harry Shum
Microsoft announced it would spin off its chatbot business XiaoIce, with all associated technologies licensed to a newly formed independent company.
ProtTrans Delivers SOTA Pretrained Language Models for Proteins
Researchers launched the ProtTrans Project, which provides an outstanding model for protein pretraining.
Introducing TayPO, a Unifying Framework for Reinforcement Learning
Researchers proposed a Taylor Expansion Policy Optimization (TayPO) framework that combines two leading algorithmic improvement methods.
Insilico Medicine Announces the Spin-Off of Deep Longevity
Insilico Medicine announced a spin-off of its aging biomarker and deep aging clock business.
ICML 2020 Announces Outstanding Paper Awards
The acceptance rate of 21.8 percent is slightly lower than 2019’s 22.6 percent (774 accepted papers from 3,424 submissions).
DeepMind Explores Generalization and Efficiency in Algorithm Design
DeepMind introduced a new approach designed to improve the generalizability and efficiency of algorithms represented by neural networks.
Viral Post Highlights ‘Toxicity Problems’ in the Machine Learning Community
The post highlights perceived peer-review problems, the reproducibility crisis, and ethics and diversity issues.
Researchers Propose ‘Neuro-Symbolic’ Approach for Generative Art
Researchers propose a neuro-symbolic hybrid approach to address the challenge of creativity in generative art.
ICML 2020 Announces Test of Time Award
Organizers of the 37th International Conference on Machine Learning (ICML) have announced this year’s Test of Time award, which goes to a team from the California Institute of Technology, University of Pennsylvania, Saarland University.
Deep Graph Contrastive Representation Learning
This paper presents a novel contrastive framework for unsupervised graph representation learning.
Stanford ‘SIRENs’ Apply Periodic Activation Functions to Implicit Neural Representations
The researchers introduce sinusoidal representation networks (SIRENs) as a method for leveraging periodic activation functions for implicit neural representations.
Fourier Feature Mapping Enables MLPs to Learn High-Frequency Functions in Low-Dimensional Domains
Researchers have proposed the use of Fourier feature mapping with MLPs in order to learn high-frequency functions in low-dimensional problem domains.
Google Brain’s SimCLRv2 Achieves New SOTA in Semi-Supervised Learning
Following on the February release of its contrastive learning framework SimCLR, the same team of Google Brain researchers guided by Turing Award honouree Dr. Geoffrey Hinton has presented SimCLRv2, an upgraded approach that boosts the SOTA results by 21.6 percent.
Answering Multi-Hop Open-Domain Questions With Graph-Based Recurrent Retrieval
Researchers from the University of Washington, Salesforce Research and Allen Institute for Artificial Intelligence have introduced a graph-based method that retrieves reasoning paths to boost multi-hop open-domain question answering.
GitHub Actions Facilitate MLOps on Repositories
GitHub recently introduced a series of free and open-source GitHub Actions that merge data science and machine learning workflows with a software development workflow.
Google Brain Rethinks Pre-training and Self-training
A team of researchers from Google Brain have proposed a rethink of the dominant computer vision paradigm of pre-training.
Local Motion Phases Technique Boosts Basketball Animation Richness and Realism
Researchers have proposed a novel framework that learns fast and dynamic character interactions.
Facebook and Kaggle Face Backlash After Disqualifying Apparent ‘Deepfake Detection Challenge’ Winner
Facebook and Kaggle are facing an online backlash after the apparent winners of the Deepfake Detection Challenge (DFDC) were disqualified.
Facebook and UC Berkeley Boost CV Performance and Lower Compute Cost With Visual Transformers
A team of researchers from Facebook and UC Berkeley has proposed a new paradigm for computer vision.
A Look at Recent Advances in Google Translate
In a recent Google AI team blog post, researchers report on recent efforts and progress in the field of language translation, especially with resource-poor languages.
Toronto Machine Learning Society Presents MLOps: Production & Engineering 2020
Toronto Machine Learning Society (TMLS) hosts MLOps, Production & Engineering 2020 through an interactive conference to enable attendees the opportunity to virtually engage with speakers and establish a stronger network within the AI community.
Unsupervised Image Classification Approach Outperforms SOTA Methods by ‘Huge Margins’
Researchers from Katholieke Universiteit Leuven in Belgium and ETH Zürich in a recent paper propose a two-step approach for unsupervised classification.
Pandemics don’t wait: How we built COVID-Net in under 7 days
Rather than simply treating AI as a tool to be leveraged, this approach reimagines AI as a collaborator that learns from a developer’s needs and subsequently proposes multiple design approaches with different trade-offs in order to enable a rapid and iterative approach to model building.
COVID-19 Contact Tracing Apps – How Good Is Good Enough?
23 respected machine learning researchers propose that personalized peer-to-peer contact tracing through mobile apps has the potential to shift the paradigm of Covid-19 community spread.
Breakthrough Colourization Technique Enables Instance-Aware Treatment of Multiple Objects
The research team proposes that colourization performance can be improved dramatically at the instance level for a few reasons.
Tsinghua & UC Berkeley | A New Meta-Baseline for Few-Shot Learning
A new simple baseline for few-shot learning that achieves state-of-the-art performance.
Cross-domain Correspondence Learning for Exemplar-based Image Translation
We present a general framework for exemplar-based image translation, which synthesizes a photo-realistic image from the input in a distinct domain, given an exemplar image.
Microsoft Build 2020 | World Top-5 Supercomputer With OpenAI, Microsoft Turing Models, Responsible ML Capabilities in AI Systems
The 48-hour digital event kicked off yesterday, and the company wasted no time making impactful announcements that included a new supercomputer, a family of large AI models, and a Responsible ML on Microsoft Azure initiative.