Skip to main content

ALBERT: A Lite BERT for Self-Supervised Learning of Language Representations

The On-Device Machine Learning Behind Recorder

Improving Out-of-Distribution Detection in Machine Learning Models

Improvements to Portrait Mode on the Google Pixel 4 and Pixel 4 XL

Fairness Indicators: Scalable Infrastructure for Fair ML Systems

Lessons Learned from Developing ML for Healthcare

Google at NeurIPS 2019

Understanding Transfer Learning for Medical Imaging

Developing Deep Learning Models for Chest X-rays with Adjudicated Image Labels

Astrophotography with Night Sight on Pixel Phones

RecSim: A Configurable Simulation Platform for Recommender Systems

New Solutions for Quantum Gravity with TensorFlow

SPICE: Self-Supervised Pitch Estimation

Introducing the Next Generation of On-Device Vision Models: MobileNetV3 and MobileNetEdgeTPU

New Insights into Human Mobility with Privacy Preserving Aggregation

Highlights from the 3rd Cohort of the Google AI Residency Program

The Visual Task Adaptation Benchmark

Learning to Assemble and to Generalize from Self-Supervised Disassembly

On-Device Captioning with Live Caption

Introducing the Schema-Guided Dialogue Dataset for Conversational Assistants

Google at ICCV 2019

A New Workflow for Collaborative Machine Learning Research in Biodiversity

Learning to Smell: Using Deep Learning to Predict the Olfactory Properties of Molecules

Quantum Supremacy Using a Programmable Superconducting Processor

Audio and Visual Quality Measurement Using Fréchet Distance

Video Architecture Search

Exploring Massively Multilingual, Massive Neural Machine Translation

ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots

Improving Quantum Computation with Classical Machine Learning

Releasing PAWS and PAWS-X: Two New Datasets to Improve Natural Language Understanding Models

Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model

Contributing Data to Deepfake Detection Research

An Inside Look at Flood Forecasting

Project Ihmehimmeli: Temporal Coding in Spiking Neural Networks

Google at Interspeech 2019

Using Deep Learning to Inform Differential Diagnoses of Skin Diseases

Learning Cross-Modal Temporal Representations from Unlabeled Videos

Recursive Sketches for Modular Deep Learning

Assessing the Quality of Long-Form Synthesized Speech

Announcing Two New Natural Language Dialog Datasets

Announcement of the 2019 Fellowship Awardees and Highlights from the Google PhD Fellowship Summit

Giving Lens New Reading Capabilities in Google Go

Exploring Weight Agnostic Neural Networks

Bi-Tempered Logistic Loss for Training Neural Nets with Noisy Data

Turbo, An Improved Rainbow Colormap for Visualization

On-Device, Real-Time Hand Tracking with MediaPipe

Joint Speech Recognition and Speaker Diarization via Sequence Transduction

Project Euphonia’s Personalized Speech Recognition for Non-Standard Speech

Video Understanding Using Temporal Cycle-Consistency Learning

EfficientNet-EdgeTPU: Creating Accelerator-Optimized Neural Networks with AutoML

An Interactive, Automated 3D Reconstruction of a Fly Brain

Robust Neural Machine Translation

Google at ACL 2019

Learning Better Simulation Methods for Partial Differential Equations

Building SMILY, a Human-Centric, Similar-Image Search Tool for Pathology

Parrotron: New Research into Improving Verbal Communication for People with Speech Impairments

Multilingual Universal Sentence Encoder for Semantic Retrieval

Advancing Semi-supervised Learning with Unsupervised Data Augmentation

Predicting the Generalization Gap in Deep Neural Networks

Announcing the YouTube-8M Segments Dataset

Predicting Bus Delays with Machine Learning

Innovations in Graph Representation Learning

Off-Policy Classification - A New Reinforcement Learning Model Selection Method

Google at CVPR 2019

Applying AutoML to Transformer Architectures

Google at ICML 2019

Introducing Google Research Football: A Novel Reinforcement Learning Environment

An Inside Look at Google Earth Timelapse

Introducing TensorNetwork, an Open Source Library for Efficient Tensor Calculations

EfficientNet: Improving Accuracy and Efficiency through AutoML and Model Scaling

Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction

Introducing Translatotron: An End-to-End Speech-to-Speech Translation Model

An End-to-End AutoML Solution for Tabular Data at KaggleDays

Announcing Open Images V5 and the ICCV 2019 Open Images Challenge

Google at ICLR 2019

Announcing Google-Landmarks-v2: An Improved Dataset for Landmark Recognition & Retrieval

Announcing the 6th Fine-Grained Visual Categorization Workshop

Evaluating the Unsupervised Learning of Disentangled Representations

SpecAugment: A New Data Augmentation Method for Automatic Speech Recognition

MorphNet: Towards Faster and Smaller Neural Networks

Take Your Best Selfie Automatically, with Photobooth on Pixel 3

Capturing Special Video Moments with Google Photos

Using Deep Learning to Improve Usability on Mobile Devices

Unifying Physics and Deep Learning with TossingBot

Simulated Policy Learning in Video Models

Reducing the Need for Labeled Data in Generative Adversarial Networks

Measuring the Limits of Data Parallel Training for Neural Networks

A Summary of the Google Flood Forecasting Meets Machine Learning Workshop

Google Faculty Research Awards 2018

Harnessing Organizational Knowledge for Machine Learning

An All-Neural On-Device Speech Recognizer

Real-Time AR Self-Expression with Machine Learning

RNN-Based Handwriting Recognition in Gboard

Exploring Neural Networks with Activation Atlases

Introducing GPipe, an Open Source Library for Efficiently Training Large-scale Neural Network Models

Long-Range Robotic Navigation via Automated Reinforcement Learning

Learning to Generalize from Sparse and Underspecified Rewards

On the Path to Cryogenic Control of Quantum Processors

Introducing PlaNet: A Deep Planning Network for Reinforcement Learning

Using Global Localization to Improve Navigation

Announcing the Second Workshop and Challenge on Learned Image Compression

Real-time Continuous Transcription with Live Transcribe

Transformer-XL: Unleashing the Potential of Attention Models

Natural Questions: a New Corpus and Challenge for Question Answering Research

Expanding the Application of Deep Learning to Electronic Health Records

Soft Actor-Critic: Deep Reinforcement Learning for Robotics

Looking Back at Google’s Research Efforts in 2018