Up Close and Personal With BERT – Google’s Epoch-Making Language Model
A recent Google Brain paper looks into Google’s hugely successful transformer network — BERT — and how it represents linguistic information internally.
Category: AI
Global machine intelligence updates.
Allen Institute’s New ‘Computer Vision Explorer’ Lets Researchers Demo SOTA CV Models
The tool enables researchers to try, compare, and evaluate models to decide which work best on their datasets or for their research purposes.
AAAI 2020 Best Papers; Turing Award Winners See a Turning Point for Deep Learning; MIT Reveals Voting App Vulnerabilities
Synced Global AI Weekly February 16th
How AI Is Changing Your Kitchen
Thanks to AI technologies such as image recognition and machine learning, people can now save time, food and money in the kitchen while discovering creative and tasty recipes and even generating their own new and personalized flavours.
What’s Happening Down There? New Aerial Video Event Recognition Dataset and DL Benchmark
The study introduces an Event Recognition in Aerial video (ERA) dataset comprising 2,866 aerial videos collected from YouTube and annotated with labels from 25 different classes corresponding to an event that can be seen unfolding over a period of five seconds.
Google Brain & CMU Semi-Supervised ‘Noisy Student’ Achieves 88.4% Top-1 Accuracy on ImageNet
Researchers from Google Brain and Carnegie Mellon University have released models trained with a semi-supervised learning method called “Noisy Student” that achieve 88.4 percent top-1 accuracy on ImageNet.
Unsupervised Approach for GAN Interpretability Through Semantic Direction Discovery
Researchers have introduced the first unsupervised learning approach for identifying interpretable semantic directions in the latent space of generative adversarial network (GAN) models.
17 Billion Parameters! Microsoft DeepSpeed Breeds World’s Largest NLP Model
Deep learning models are getting larger and larger to meet the demand for better and better performance. Meanwhile, the timeContinue Reading
Beyond SPADE: Introducing Semantic Region-Adaptive Normalization for Image Synthesis
Researchers introduced semantic region-adaptive normalization (SEAN), a simple but effective building block for conditional Generative Adversarial Networks (cGAN).
AAAI 2020 | A Turning Point for Deep Learning? Hinton, LeCun, and Bengio Might Have Different Approaches
The Godfathers of AI and 2018 ACM Turing Award winners Geoffrey Hinton, Yann LeCun, and Yoshua Bengio shared a stage in New York on Sunday night at an event organized by the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020).
Facebook Open-Sources PyTorch3D CV Library
In a bid to simplify 3D deep learning and improve processing performance and efficiency, Facebook recently introduced an open-source framework for 3D computer vision.
Research Roundup: Science & Technology Versus the 2019 Novel Coronavirus
Synced Global AI Weekly February 9th
Battling the Coronavirus: Alibaba and Baidu AI Accelerate Vaccine and Drug R&D
The crucial step now is to develop matching vaccines and drugs to uproot its existence, and China’s big tech companies have stepped up to help.
Share My Research | Batchboost: Regularization for Stabilizing Training With Resistance to Underfitting & Overfitting
Batchboost is a simple technique to accelerate ML model training by adaptively feeding mini-batches with artificial samples which are created by mixing two examples from the previous step – in favor of pairing those that produce the difficult one.
Sing Along! Japanese Researchers Develop Multispeaker Corpus for Singing Voice Synthesis
In an effort to enrich resources for multispeaker singing-voice synthesis, a team of researchers from the University of Tokyo has developed a Japanese multispeaker singing-voice corpus.
Radioactive Data: Facebook AI Knows Where You Got Your Training Dataset
Researchers proposed a “radioactive data” technique for subtly marking images in a dataset to help researchers later determine whether they were used to train a particular model.
Machine Unlearning: Fighting for the Right to Be Forgotten
In a new paper, researchers from the University of Toronto, Vector Institute, and University of Wisconsin-Madison propose SISA training, a new framework that helps models “unlearn” information by reducing number of updates that need to be computed when data points are removed.
Using Rotation, Translation, and Cropping to Boost Generalization in Deep Reinforcement Learning Models
In a new paper, researchers from the New York University and Modl.ai, a company applying machine learning to game developing, suggest that simple spacial processing methods such as rotation, translation and cropping could help increase model generality.
Baidu Open-Sources RNA Prediction Algorithm for 2019 Novel Coronavirus
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.
Facebook HiPlot ‘Makes Understanding High Dimensional Data Easy’
Facebook’s new HiPlot is a lightweight interactive visualization tool that takes this further, using parallel plots to discover correlations and patterns in such high-dimensional data.
A Look at ‘Escaping From Saddle Points on Riemannian Manifolds’
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.
AI Tackles the 2019 Novel Coronavirus, Anemia and More; OpenAI Switches to PyTorch
Synced Global AI Weekly February 2nd
Pet Retail Market Chases Smart Products
Advancements in machine learning in recent years have enabled a number of novel offerings in the pet retail market, pushing smart pet products sales to US$565 million in 2018.
DeepMind & UCL Introduce New Model and Test Set for Inference
Now, DeepMind and University College London (UCL) have introduced a new deep network called MEMO which matches SOTA results on Facebook’s bAbI dataset for testing text understanding and reasoning, and is the first and only architecture capable of solving long sequence novel reasoning tasks.
Scientists Use DL and Other Tools for 2019 Novel Coronavirus Host and Infectivity Prediction
A new study suggests human-to-human transmission of the 2019 Novel Coronavirus (2019-nCoV) may have started as early as mid December, 2019.
Meet Meena: A Truly Chatty Chatbot
One of a new breed of open-domain chatbots designed to engage in conversations across any topic, Meena’s free and natural conversational abilities are closing the gap on human performance.
Facebook AI mBART: The Tower of Babel’s Silicon Solution
Facebook AI researchers have further developed the BART model with the introduction of mBART.
AraNet: New Deep Learning Toolkit for Arabic Social Media
A team of researchers from the Natural Language Processing Lab at the University of British Columbia in Canada have proposed AraNet, a deep learning toolkit designed for Arabic social media processing.
New Study Suggests Self-Attention Layers Could Replace Convolutional Layers on Vision Tasks
Inspired by the performance of attention mechanisms in NLP, researchers have explored the possibility of applying them to vision tasks.
Can AlphaZero Leap From Go & Chess to Quantum Computing?
A new study suggests DeepMind’s amazing game-playing algorithm AlphaZero could help unlock the power and potential of quantum computing.
Next Generation ArXiv and the Economics of Open Access Publishing
Making science accessible for all is a wonderful and enriching proposal. Unfortunately the execution is not that easy — and nobody knows this better than the team that pioneered arXiv, the world’s largest free scientific paper repository.
Microsoft ImageBERT | Cross-modal Pretraining with Large-scale Image-Text Data
A recent paper published by Microsoft researchers proposes a new vision-language pretrained model for image-text joint embedding, ImageBERT, which which achieves SOTA performance on both the MSCOCO and Flickr30k datasets.
AI Headhunters & Tech Trends in Global Talent Recruitment
Over 80 percent of corporate survey respondents expect to see an increased use of technology in recruiting sourcing/outreach, candidate screening, and applications, while most also see the tech being used in candidate assessment and compensation package generation.
NLPR, SenseTime & NTU Accelerate Automatic Video Portrait Editing
Researchers from Beijing’s National Laboratory of Pattern Recognition (NLPR), SenseTime Research, and Nanyang Technological University have taken the tech one step further with a new framework that enables totally arbitrary audio-video translation.
Hallo! Hallo! KU Leuven & TU Berlin Introduce ‘RobBERT,’ a SOTA Dutch BERT
A group of researchers from The Katholieke Universiteit Leuven and The Technical University of Berlin recently introduced a Dutch RoBERTa-based language model, RobBERT.
Google FixMatch: SOTA Performance on Semi-Supervised Learning Benchmarks
A team from Google Research introduced FixMatch, an algorithm that combines two common SSL methods for deep networks: pseudo-labeling (aka self-training) and consistency regularization.
Autonomous Learning Library Simplifies Intelligent Agent Creation
The Autonomous Learning Library is a deep reinforcement learning (DRL) library for PyTorch that streamlines the building and evaluation of novel reinforcement learning agents.
New Large Aerial Image Database for Agricultural Pattern Analysis
AI systems are already helping farmers with soil analysis, planting, animal husbandry, water conservation and more.
Google Introduces Flax: A Neural Network Library for JAX
Google recently introduce Flax - a neural network library for JAX that is designed for flexibility.